© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9627
    Prev
    Next
    INDEX
    Explanations

    code context or punctuation

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

    The neuron specializes in spotting isolated punctuation and formatting tokens (e.g. quotes, parentheses, colons, and similar symbols) often used in code or format strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "+
    0.73
    "(
    0.70
    "...
    0.66
    Crash
    0.64
    "-
    0.63
    Bold
    0.63
     .......
    0.62
    Minus
    0.60
    」(
    0.60
    Bj
    0.59
    POSITIVE LOGITS
     ')[
    0.67
    _',
    0.65
    .');
    0.64
     menjaga
    0.57
     troupe
    0.57
     demur
    0.57
     diaspora
    0.55
     demeure
    0.55
     heur
    0.54
     plag
    0.54
    Activations Density 0.011%

    No Known Activations