© 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. 28348
    Prev
    Next
    INDEX
    Explanations

    special characters in code

    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
    )’
    -2.77
    厯
    -2.34
    ’).
    -2.27
    玙
    -2.25
    頹
    -2.25
    ’)
    -2.25
    鸰
    -2.20
     ansehen
    -2.19
    趼
    -2.17
    jdons
    -2.11
    POSITIVE LOGITS
     '
    4.47
    [
    3.00
    ...
    2.92
    依然
    2.77
    --
    2.70
    The
    2.64
    H
    2.53
    —
    2.52
    ---
    2.47
    除了
    2.47
    Activations Density 0.265%

    No Known Activations