© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31611
    Prev
    Next
    INDEX
    Explanations

    subscribe to

    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_34/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
     január
    -1.09
     година
    -0.89
     need
    -0.88
     Tenggara
    -0.87
    нон
    -0.86
    需要
    -0.85
    ссив
    -0.82
     Kommune
    -0.82
    년
    -0.81
     ``
    -0.80
    POSITIVE LOGITS
     RIG
    0.95
     vielfach
    0.94
    它們
    0.93
     lair
    0.90
     prochaines
    0.87
     haiku
    0.87
    ダン
    0.84
     همان
    0.83
     FRESH
    0.82
     Shrek
    0.82
    Activations Density 0.000%

    No Known Activations