© 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. 22263
    Prev
    Next
    INDEX
    Explanations

    hearing from others

    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
    <bos>
    -2.27
     Wortes
    -1.77
     angebra
    -1.77
     comodidad
    -1.70
    乐观
    -1.69
    儈
    -1.65
     vorsichtig
    -1.65
     jiné
    -1.63
     
    -1.62
     стоковая
    -1.59
    POSITIVE LOGITS
    謌
    2.03
    alakip
    1.80
    癀
    1.78
     saat
    1.77
     you
    1.73
    明月
    1.73
     o
    1.70
     dalam
    1.66
     meren
    1.65
    ሖ
    1.62
    Activations Density 0.002%

    No Known Activations