© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13883
    Prev
    Next
    INDEX
    Explanations

    code index variables

    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
     颜色
    -1.09
     discípulos
    -1.05
     Köz
    -1.02
     Sénat
    -0.97
    Odpo
    -0.96
    svm
    -0.96
    npj
    -0.94
    ब्द
    -0.93
    Dónde
    -0.93
    mitsubishi
    -0.92
    POSITIVE LOGITS
    而且
    0.98
    pretty
    0.98
    ap
    0.98
     milliards
    0.97
    ↵
    0.91
     細
    0.90
     поколения
    0.89
    bool
    0.88
    force
    0.88
    ards
    0.88
    Activations Density 0.003%

    No Known Activations