© 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. 15782
    Prev
    Next
    INDEX
    Explanations

    code identifiers and syntax

    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
     altre
    -1.03
     by
    -0.93
    完成です
    -0.93
     other
    -0.91
     before
    -0.90
    drawSprites
    -0.90
    癖
    -0.87
    いただく
    -0.86
    codehaus
    -0.84
     three
    -0.84
    POSITIVE LOGITS
     présentes
    0.99
     különböző
    0.97
     Crum
    0.92
     noires
    0.89
    色々な
    0.88
     cubiertos
    0.88
     GNA
    0.88
     variedad
    0.88
     Achieve
    0.86
     ſmall
    0.86
    Activations Density 0.011%

    No Known Activations