© 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. 113134
    Prev
    Next
    INDEX
    Explanations

    change makers and savers

    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
    </h3>
    -2.53
    "));
    -1.70
     quot
    -1.62
     Vordergrund
    -1.53
    karz
    -1.53
     erstes
    -1.52
     hauptsächlich
    -1.52
     destrucción
    -1.52
    chenen
    -1.51
    ";
    -1.48
    POSITIVE LOGITS
    </b>
    2.22
    $,
    1.85
    isitions
    1.66
     Saltar
    1.63
    欒
    1.57
    LETED
    1.52
    tles
    1.48
    That
    1.48
     I
    1.47
    言えば
    1.46
    Activations Density 0.003%

    No Known Activations