© 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. 118867
    Prev
    Next
    INDEX
    Explanations

    interface dimensions and code attributes

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

    The neuron fires on standalone numeric literals (numbers) embedded in code or markup.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    github
    -1.22
    fmt
    -0.98
     github
    -0.83
    mPaint
    -0.82
    Atentamente
    -0.80
     fmt
    -0.77
    Specifik
    -0.76
    痤
    -0.76
    usos
    -0.73
    Its
    -0.72
    POSITIVE LOGITS
    cotta
    0.90
    徵
    0.76
    bmw
    0.75
     replaceable
    0.75
    brück
    0.75
     should
    0.75
     berücksichtigt
    0.75
     باید
    0.74
    تف
    0.74
    ptus
    0.73
    Activations Density 0.004%

    No Known Activations