© 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. 22-GEMMASCOPE-RES-131K
    7. 72204
    Prev
    Next
    INDEX
    Explanations

    function and callback usage

    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
    KNOWN
    -0.89
     nasel
    -0.86
     tròn
    -0.85
    Cringe
    -0.85
    SPOILERS
    -0.84
     THEATRE
    -0.84
     Aufgrund
    -0.84
    ilangkan
    -0.82
     Handlungen
    -0.82
    guas
    -0.81
    POSITIVE LOGITS
     criteria
    1.05
    每
    1.02
     reaction
    1.02
     מדי
    0.99
     or
    0.99
    return
    0.97
     उत्पाद
    0.96
    ysk
    0.94
     creativity
    0.93
     psychologie
    0.91
    Activations Density 0.049%

    No Known Activations