© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14316
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and quantification

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

    This neuron detects numeric literals (digits and numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    erobic
    -1.07
     人民
    -0.98
     from
    -0.98
    archical
    -0.94
     such
    -0.93
     anta
    -0.92
     satunya
    -0.91
     raste
    -0.91
    삭
    -0.91
    {$\
    -0.90
    POSITIVE LOGITS
    ザー
    0.95
     fisuras
    0.92
     elke
    0.90
     vient
    0.88
     же
    0.88
     terminée
    0.86
     espalda
    0.84
    Economía
    0.84
     ws
    0.84
    savvy
    0.82
    Activations Density 0.006%

    No Known Activations