© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128577
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numeric literals (tokens composed of digits) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    barbie
    -0.97
    djang
    -0.94
    calvin
    -0.94
    batman
    -0.94
    samurai
    -0.93
    gitlab
    -0.91
    plush
    -0.90
    ansvar
    -0.89
     trúc
    -0.89
    cibo
    -0.88
    POSITIVE LOGITS
     if
    0.95
     yours
    0.91
     atât
    0.86
     regra
    0.85
    if
    0.85
     LAG
    0.85
     Yours
    0.84
    Checks
    0.82
    mybatisplus
    0.79
    がこの
    0.79
    Activations Density 0.005%

    No Known Activations