© 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. 128922
    Prev
    Next
    INDEX
    Explanations

    foreign words and symbols

    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
     through
    -1.00
     where
    -0.94
     which
    -0.93
     to
    -0.92
    を感じ
    -0.91
     algod
    -0.91
    っかり
    -0.89
    袭击
    -0.88
     приготовить
    -0.88
     manifestación
    -0.88
    POSITIVE LOGITS
     MÉXICO
    1.02
    Ke
    0.98
     dessous
    0.92
     quella
    0.91
     車
    0.91
     eftersom
    0.88
    mml
    0.86
    imo
    0.86
     cuarent
    0.85
     vouloir
    0.85
    Activations Density 0.008%

    No Known Activations