© 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. 62911
    Prev
    Next
    INDEX
    Explanations

    version or license text

    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
     teneur
    -0.84
     Syntax
    -0.84
    </td>
    -0.75
     jakość
    -0.73
    haust
    -0.73
    瓠
    -0.72
     began
    -0.72
    (';
    -0.72
    Πηγές
    -0.72
    mögen
    -0.71
    POSITIVE LOGITS
     INTERNATIONAL
    0.86
     dependencia
    0.84
    绒
    0.82
     języ
    0.77
     международ
    0.75
     официаль
    0.74
    Oby
    0.73
    цька
    0.71
     expertos
    0.71
     kê
    0.69
    Activations Density 0.003%

    No Known Activations