© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68534
    Prev
    Next
    INDEX
    Explanations

    comma separated values

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

    The neuron is detecting comma characters used as separators.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    commas used as separators or delimiters, including mentions of a comma in text.

    oai_token-act-pair · gpt-5
    Triggered by @jyhe0408

    commas in structured data formats like JSON, CSV, and code.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered 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
    Negative Logits
    for
    -1.79
    "
    -1.76
    *
    -1.74
    [
    -1.69
    {
    -1.65
     now
    -1.59
     was
    -1.58
    s
    -1.49
     они
    -1.49
    now
    -1.49
    POSITIVE LOGITS
    hline
    2.14
    hellip
    1.90
    ()];
    1.90
    fi
    1.88
    ff
    1.84
    뿡
    1.83
     ſmall
    1.81
    ())),
    1.80
     схемы
    1.80
    vencia
    1.80
    Activations Density 0.145%

    No Known Activations