© 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. 106992
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    providedIn
    -1.02
    ешь
    -1.00
    视着
    -1.00
    ！(
    -0.98
    \,.
    -0.98
     najdete
    -0.98
     recommandée
    -0.97
    fstream
    -0.96
     any
    -0.95
     MenuView
    -0.95
    POSITIVE LOGITS
    import
    1.04
    until
    1.01
    r
    1.00
     uti
    0.97
    o
    0.93
    ↵
    0.93
     ati
    0.91
    often
    0.91
     UNIC
    0.90
    overall
    0.89
    Activations Density 0.002%

    No Known Activations