© 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. 10-GEMMASCOPE-RES-131K
    7. 67237
    Prev
    Next
    INDEX
    Explanations

    Ivory Coast

    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_10/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
    K
    -1.99
    ll
    -1.97
    ${
    -1.84
    W
    -1.78
    ات
    -1.78
     Gespräche
    -1.73
    U
    -1.71
    6
    -1.69
     продажи
    -1.69
     erklär
    -1.69
    POSITIVE LOGITS
    <td>
    1.84
    ization
    1.77
    </strong>
    1.66
    Ivoire
    1.59
    ção
    1.55
    方に
    1.44
    clerosis
    1.44
    歿
    1.41
    潜力
    1.41
    ueel
    1.39
    Activations Density 0.021%

    No Known Activations