© 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. 106687
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commands

    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
    さぁ
    -1.02
    See
    -0.98
    あー
    -0.98
    たまに
    -0.94
     einschließlich
    -0.93
    wiście
    -0.93
    すっ
    -0.92
    あんまり
    -0.91
    あぁ
    -0.90
     moron
    -0.88
    POSITIVE LOGITS
    ﾌ
    0.91
     paš
    0.91
    Table
    0.91
    zenden
    0.89
    tividade
    0.89
    ]):
    0.87
    ztes
    0.87
    漱
    0.86
    kungan
    0.84
     Appendix
    0.84
    Activations Density 0.022%

    No Known Activations