© 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. 68340
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     of
    -2.50
     that
    -1.74
     by
    -1.70
     for
    -1.51
     if
    -1.46
     to
    -1.46
     on
    -1.41
     meskipun
    -1.36
     indivíduo
    -1.35
    D
    -1.34
    POSITIVE LOGITS
     produrre
    1.64
     seguras
    1.53
     realizzare
    1.48
     encontramos
    1.45
     plataformas
    1.41
    jų
    1.40
     sientes
    1.39
     excelentes
    1.37
     بهداشتی
    1.36
     permitir
    1.34
    Activations Density 0.009%

    No Known Activations