Federated SPARQL query processing allows to query multiple interlinked datasets hosted by remote SPARQL endpoints. However, finding pertinent federated queries over a growing number of datasets is challenging. In this paper, we propose PFed, an approach to recommend plausible federated queries based on query logs of different datasets. The problem is not to find similar federated queries, but plausible complementary queries over different datasets. Starting with a real SPARQL query log, PFed stretches the query with real queries from different logs. A generated federated query Q is plausible if an external observer cannot deny that queries in the original logs could be subqueries of Q. PFed relies on data summaries and real SPARQL query logs to generate plausible federated queries. It starts by pruning the queries logs by selecting only queries with joinable predicates. Experimental results with real logs of DBpedia and SWDF demonstrate that PFed is able to prune drastically the logs and recommend realistic federated queries.