© 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. 74083
    Prev
    Next
    INDEX
    Explanations

    closing brackets, parentheses, and fractions

    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
    er
    -3.33
    (
    -3.20
    [
    -3.00
    ه
    -2.88
     --
    -2.88
     ---
    -2.86
    For
    -2.78
     Shortly
    -2.77
    9
    -2.73
     Honestly
    -2.69
    POSITIVE LOGITS
    樒
    3.06
     lác
    3.02
    圌
    2.94
    Ɑ
    2.81
    垕
    2.78
    ⑊
    2.72
    ⏑
    2.69
    鼍
    2.67
    珰
    2.66
    臜
    2.66
    Activations Density 0.002%

    No Known Activations