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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 600
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
    鸶
    -3.20
    Ꭳ
    -3.02
    趼
    -2.84
    蚴
    -2.77
    because
    -2.66
    鼋
    -2.61
    淠
    -2.56
    皤
    -2.55
     Это
    -2.52
    轵
    -2.52
    POSITIVE LOGITS
    {
    3.92
     was
    3.09
    s
    2.95
    ↵↵
    2.88
     {
    2.78
    a
    2.72
    o
    2.72
    )
    2.67
    m
    2.61
     scr
    2.53
    Activations Density 0.011%

    No Known Activations