© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15989
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

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

    This neuron fires on numeric constants (including floats) and arithmetic‐operator sequences within code or math expressions.

    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
     termed
    -0.96
    (/*
    -0.93
     anfangen
    -0.90
    bbt
    -0.89
    ार
    -0.88
    命的
    -0.88
     supposition
    -0.85
     U
    -0.85
     Its
    -0.84
     <
    -0.84
    POSITIVE LOGITS
    ]));
    1.00
    //};
    1.00
     hatta
    0.91
    鹇
    0.91
     modele
    0.90
     pozor
    0.90
    ecimento
    0.90
    ularity
    0.90
     cyclisme
    0.89
    ſſen
    0.88
    Activations Density 0.001%

    No Known Activations