© 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. 14670
    Prev
    Next
    INDEX
    Explanations

    in this context; as used herein

    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
    犼
    -1.80
    蚡
    -1.78
    魆
    -1.70
     zonder
    -1.68
    魮
    -1.66
    sont
    -1.66
    lø
    -1.55
     personalización
    -1.52
     ventilación
    -1.52
     banheiro
    -1.50
    POSITIVE LOGITS
    //
    1.73
     improving
    1.73
    on
    1.71
     modifying
    1.65
    茘
    1.63
    uitton
    1.59
    他对
    1.59
    ၟ
    1.59
    ll
    1.59
    لمانيا
    1.58
    Activations Density 0.058%

    No Known Activations