© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20441
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    The neuron primarily fires on programming punctuation—especially statement‐ending semicolons.

    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
    ’
    -1.63
    —”
    -1.61
    ...”
    -1.59
    also
    -1.56
     februari
    -1.52
    If
    -1.47
    …”
    -1.47
    呖
    -1.45
    ”.
    -1.45
    ?”
    -1.45
    POSITIVE LOGITS
    prechung
    1.41
     refrigerador
    1.39
     nyní
    1.38
    特有
    1.35
     особенно
    1.35
    mės
    1.34
     kteří
    1.34
    collana
    1.34
    ândia
    1.32
     vicinity
    1.31
    Activations Density 0.005%

    No Known Activations