© 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. 10-GEMMASCOPE-RES-131K
    7. 9686
    Prev
    Next
    INDEX
    Explanations

    diet and sale

    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
     Даже
    -1.71
    there
    -1.71
    end
    -1.64
     grima
    -1.61
    ждении
    -1.55
    というわけで
    -1.48
    瀦
    -1.46
     quarrels
    -1.41
     Conflicts
    -1.40
     Поэтому
    -1.38
    POSITIVE LOGITS
    ↵↵
    1.88
     möjligt
    1.73
     of
    1.63
     只
    1.62
     自己
    1.54
     gärna
    1.52
     叶子
    1.50
    蠖
    1.49
     kanskje
    1.48
     they
    1.47
    Activations Density 0.017%

    No Known Activations