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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40498
    Prev
    Next
    INDEX
    Explanations

    sudden, collaborators, majored

    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
     всѣ
    -1.95
     ćwic
    -1.87
     sorpresas
    -1.85
    肫
    -1.85
     montaż
    -1.84
    蹓
    -1.83
    archiviato
    -1.81
     obsługi
    -1.81
     zesta
    -1.79
    typer
    -1.77
    POSITIVE LOGITS
     if
    2.33
     for
    1.93
     of
    1.92
     because
    1.86
     when
    1.84
     also
    1.83
     in
    1.80
    in
    1.78
     to
    1.75
     then
    1.70
    Activations Density 0.350%

    No Known Activations