© 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. 33804
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    //}
    -0.93
     тыс
    -0.91
     május
    -0.91
    ocumented
    -0.91
     améli
    -0.90
    출
    -0.89
    __;
    -0.88
     sendiri
    -0.87
    ▻
    -0.86
    inheritDoc
    -0.85
    POSITIVE LOGITS
     each
    1.16
    GFR
    0.90
     Desenvolvimento
    0.84
    chenden
    0.82
    各種
    0.81
    Berat
    0.79
    Ilustra
    0.78
     Flin
    0.77
    ittles
    0.77
    据说
    0.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.