© 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. 10-GEMMASCOPE-RES-131K
    7. 43809
    Prev
    Next
    INDEX
    Explanations

    introduction headings

    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
    (
    -1.81
    一个小
    -1.80
    ().
    -1.76
    {\
    -1.73
    -
    -1.72
     said
    -1.64
    providedIn
    -1.57
    ૉ
    -1.56
    ।
    -1.54
    ()
    -1.50
    POSITIVE LOGITS
     cinquième
    1.95
     troisième
    1.68
    Vegeu
    1.63
    Boas
    1.60
    oczes
    1.59
     Noviembre
    1.55
    Basta
    1.55
    趼
    1.53
     Septiembre
    1.52
     récompense
    1.52
    Activations Density 0.003%

    No Known Activations