© 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. 10-GEMMASCOPE-RES-131K
    7. 128634
    Prev
    Next
    INDEX
    Explanations

    judicial titles and court opinions

    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
    ــــــــ
    -1.91
     kapak
    -1.73
     vestidos
    -1.69
    insel
    -1.63
     sosis
    -1.62
     horaires
    -1.61
     obtenir
    -1.60
     maravill
    -1.59
     downloaden
    -1.59
     italien
    -1.58
    POSITIVE LOGITS
    大部分
    1.69
     чаще
    1.69
    但是在
    1.65
     mostly
    1.65
     presumably
    1.62
     at
    1.60
     Tatsache
    1.60
     Unless
    1.59
     for
    1.57
     aktuellen
    1.57
    Activations Density 0.004%

    No Known Activations