© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114239
    Prev
    Next
    INDEX
    Explanations

    argument, exceptions, calendars

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

    This neuron fires on occurrences of the word “argument” (including “Argument” in exception names and error messages).

    oai_token-act-pair · o4-mini
    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
    or
    -2.27
     للاس
    -2.09
     koos
    -2.00
    栳
    -1.98
    It
    -1.98
     türk
    -1.95
    🌟
    -1.91
    ాని
    -1.90
     trent
    -1.89
     turun
    -1.88
    POSITIVE LOGITS
    
    2.27
    汌
    2.17
     Importantly
    2.16
    乃是
    2.16
    そういえば
    2.16
    淠
    2.14
    がなく
    2.14
    锇
    2.11
    $,
    2.09
    のみ
    2.03
    Activations Density 0.001%

    No Known Activations