© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15577
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis in code

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

    This neuron detects numeric literals (tokens composed of digits) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     arrivent
    -0.92
    yot
    -0.89
     estándar
    -0.88
     largura
    -0.88
    ैक
    -0.88
     ۱۶
    -0.85
     ۸
    -0.84
     siempre
    -0.84
     cão
    -0.84
     lucro
    -0.82
    POSITIVE LOGITS
     which
    1.06
    rostis
    0.96
    wości
    0.95
     блюда
    0.93
     جاده
    0.89
    ,',
    0.88
    ⬇
    0.88
    diksi
    0.88
    〘
    0.87
     subsequently
    0.86
    Activations Density 0.014%

    No Known Activations