© 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. 39688
    Prev
    Next
    INDEX
    Explanations

    Notre Dame

    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
    翃
    -2.92
    廔
    -2.73
     '
    -2.59
    Setelah
    -2.55
    飏
    -2.55
     compradores
    -2.52
    🧌
    -2.50
     *
    -2.50
    ortiment
    -2.48
    ramientas
    -2.45
    POSITIVE LOGITS
    0
    3.34
    <
    3.08
     It
    2.78
    2
    2.63
    .”
    2.63
    ).
    2.56
    (
    2.50
    %
    2.45
    +
    2.44
    i
    2.42
    Activations Density 0.003%

    No Known Activations