© 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. 10-GEMMASCOPE-RES-131K
    7. 59126
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

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

    This neuron fires on the commas that separate column names (e.g. “`,`”) in SQL CREATE/INSERT statements.

    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
    蕺
    -2.92
    婓
    -2.91
    </h2>
    -2.91
    ated
    -2.88
    牐
    -2.86
    0
    -2.75
    酲
    -2.61
    ープン
    -2.55
    𖥦
    -2.55
     denna
    -2.50
    POSITIVE LOGITS
     they
    2.86
    窳
    2.69
     使っ
    2.69
    のような
    2.44
     She
    2.42
    的很
    2.41
    </u>
    2.34
    僦
    2.34
    她
    2.34
    ();
    2.30
    Activations Density 0.003%

    No Known Activations