© 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. 86275
    Prev
    Next
    INDEX
    Explanations

    field, conduction, window, frequency, groups, collector

    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
    达到
    -1.17
    cích
    -1.16
     nasze
    -1.15
    结果
    -1.12
    开始
    -1.09
    ou
    -1.08
    你需要
    -1.07
     that
    -1.06
    ara
    -1.05
     制
    -1.05
    POSITIVE LOGITS
     sés
    1.22
     blé
    1.22
     maïs
    1.21
     vinaigre
    1.20
    Затем
    1.16
     GameState
    1.16
     лука
    1.12
     sirop
    1.12
    酲
    1.10
     their
    1.09
    Activations Density 0.389%

    No Known Activations