© 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. 44272
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and braces

    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
    <h2>
    -1.98
    <blockquote>
    -1.85
    ７
    -1.80
    它
    -1.80
    It
    -1.78
    MERS
    -1.77
    \
    -1.73
    　　　
    -1.71
    $
    -1.70
    ３
    -1.70
    POSITIVE LOGITS
     their
    1.68
     querían
    1.67
    Distribución
    1.58
     our
    1.50
    ٶ
    1.49
     which
    1.46
    Producción
    1.45
     have
    1.41
    Artis
    1.38
     読む
    1.37
    Activations Density 0.034%

    No Known Activations