© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98620
    Prev
    Next
    INDEX
    Explanations

    before conjunctions and prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kulak
    -1.34
     kazak
    -1.30
     paie
    -1.29
     diriger
    -1.27
     varier
    -1.27
     Karakter
    -1.26
     applau
    -1.24
     maniere
    -1.24
     tranſ
    -1.23
     tromper
    -1.23
    POSITIVE LOGITS
     in
    1.45
     During
    1.35
     when
    1.34
     In
    1.32
     during
    1.31
     Since
    1.30
     for
    1.29
     regarding
    1.27
     after
    1.23
     When
    1.22
    Activations Density 0.137%

    No Known Activations