© 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. 34-GEMMASCOPE-RES-131K
    7. 56990
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

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

    The neuron consistently fires on multi‐digit numeric literals in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    rab
    -0.69
    看出
    -0.68
    igare
    -0.68
    nen
    -0.67
    Kno
    -0.66
    drawRect
    -0.66
    憲
    -0.66
    宪
    -0.66
    赖
    -0.66
    licus
    -0.65
    POSITIVE LOGITS
     Guillaume
    0.72
     Symptome
    0.68
     сре
    0.68
     Somer
    0.67
     futebol
    0.67
     мода
    0.67
    GENERATED
    0.66
     Erkrankungen
    0.66
     sezonu
    0.65
     Bolsonaro
    0.65
    Activations Density 0.085%

    No Known Activations