© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38655
    Prev
    Next
    INDEX
    Explanations

    char literal or C string

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on occurrences of the C data‐type keyword “char.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ↵
    -4.06
     sacerdotes
    -2.94
     acredita
    -2.81
    撄
    -2.77
    jų
    -2.73
    ﮭ
    -2.70
    </em>
    -2.67
    泂
    -2.55
    鳢
    -2.55
    搥
    -2.55
    POSITIVE LOGITS
    '
    3.42
    er
    3.36
    3
    3.30
    2
    3.19
    ar
    3.13
    7
    2.97
    8
    2.94
    5
    2.88
    In
    2.86
     the
    2.78
    Activations Density 0.016%

    No Known Activations