© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86646
    Prev
    Next
    INDEX
    Explanations

    obtaining a copy

    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
    '
    -2.56
    瞠
    -1.80
     pratos
    -1.74
     cadeiras
    -1.70
     pelicula
    -1.67
    耵
    -1.66
    将他
    -1.66
    の家
    -1.62
     permettent
    -1.60
     республи
    -1.59
    POSITIVE LOGITS
    𐐪
    2.06
    𐄙
    1.87
    ad
    1.83
     ‘’
    1.80
    時には
    1.78
    replyreport
    1.77
    uarga
    1.77
     может
    1.77
    CurtirCurtir
    1.76
    ?),
    1.71
    Activations Density 0.034%

    No Known Activations