© 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. 10-GEMMASCOPE-RES-131K
    7. 75596
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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_10/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
     mân
    -2.41
    瑒
    -2.25
     werd
    -2.03
     mey
    -2.02
     tă
    -2.00
    上げた
    -1.94
     brilhante
    -1.93
     vermelho
    -1.93
     ofte
    -1.91
     comprometido
    -1.91
    POSITIVE LOGITS
     to
    2.67
    Only
    2.45
     (
    2.33
     [
    2.11
     of
    2.03
     設計
    1.99
    tedì
    1.97
    Just
    1.95
     только
    1.95
     from
    1.94
    Activations Density 0.001%

    No Known Activations