© 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. 43696
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

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

    The neuron responds to isolated punctuation tokens (e.g. operators like “+”, “-”, “/–” and quotation marks) rather than letters or words.

    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
    
    -1.80
    ساء
    -1.80
    طي
    -1.77
    焄
    -1.73
     their
    -1.71
     This
    -1.70
    There
    -1.67
     Sehr
    -1.66
     картинка
    -1.66
     When
    -1.66
    POSITIVE LOGITS
    '
    3.45
     Mère
    2.00
     suscripción
    1.97
    ︲
    1.95
     défi
    1.92
    "
    1.92
     '
    1.91
     tranſ
    1.89
     ity
    1.88
    ならでは
    1.86
    Activations Density 0.069%

    No Known Activations