© 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. 22-GEMMASCOPE-RES-131K
    7. 130357
    Prev
    Next
    INDEX
    Explanations

    paths and file separators

    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_22/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
    ote
    -1.05
     Aún
    -0.98
    uable
    -0.94
     einwand
    -0.94
     eventual
    -0.94
     "'
    -0.94
     SURE
    -0.92
    sertation
    -0.91
    quisite
    -0.91
     Debido
    -0.91
    POSITIVE LOGITS
    ográ
    1.05
    相続
    1.02
    ;
    1.02
     magasiner
    0.96
     horarios
    0.96
    Lorsque
    0.96
    彼は
    0.94
    kowania
    0.93
     ",";
    0.93
    ();
    0.89
    Activations Density 0.019%

    No Known Activations