© 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. 34-GEMMASCOPE-RES-131K
    7. 62907
    Prev
    Next
    INDEX
    Explanations

    interface methods and inheritance

    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_34/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
    プル
    -0.86
     mengha
    -0.85
    BBS
    -0.82
    tujuan
    -0.81
     tummy
    -0.79
     rostros
    -0.77
    Reich
    -0.77
     bague
    -0.77
     Correlation
    -0.77
     pru
    -0.77
    POSITIVE LOGITS
     näher
    0.76
     sustained
    0.75
     clearly
    0.73
     typelib
    0.71
     слова
    0.70
    ounds
    0.67
     Rezept
    0.66
    行走
    0.66
     registrada
    0.66
     buckwheat
    0.66
    Activations Density 0.019%

    No Known Activations