© 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. 772
    Prev
    Next
    INDEX
    Explanations

    up to limits

    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
    سجيلات
    -2.67
     of
    -2.66
     '
    -2.61
    mathrm
    -2.58
    ;
    -2.39
    .''
    -2.36
    .
    -2.30
    *{\
    -2.23
    『
    -2.22
    か
    -2.20
    POSITIVE LOGITS
    鐿
    2.84
    鯷
    2.38
    Зміст
    2.27
    笮
    2.20
    镬
    2.16
    龌
    2.14
    愎
    2.11
    ❊
    2.08
    𞤪
    2.06
    ねー
    2.00
    Activations Density 0.001%

    No Known Activations