© 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. 42640
    Prev
    Next
    INDEX
    Explanations

    Q: and How

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

    This neuron detects the start of line comments indicated by “//” 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_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
    er
    -2.02
    ・・・・・
    -1.80
    _
    -1.80
    するの
    -1.69
    ・・・・
    -1.66
    {
    -1.65
    ⁈
    -1.65
    韃
    -1.62
     potwier
    -1.62
    [
    -1.61
    POSITIVE LOGITS
     crème
    1.57
    गो
    1.55
    CHREIBUNG
    1.54
    蚡
    1.54
    "]);
    1.52
    垕
    1.48
     ไม่
    1.48
    Autoritní
    1.45
    阏
    1.44
    CMAKE
    1.43
    Activations Density 0.000%

    No Known Activations