© 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. 58298
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming languages

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

    This neuron detects numeric literals (numbers) in code or data.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -2.25
    6
    -2.13
    2
    -1.88
    <bos>
    -1.81
     for
    -1.80
     to
    -1.75
    9
    -1.75
    4
    -1.67
    7
    -1.63
     gången
    -1.58
    POSITIVE LOGITS
    wherein
    1.62
    commonly
    1.57
     silicona
    1.55
     cuarzo
    1.55
     Infór
    1.55
     seraient
    1.54
    showed
    1.54
    慙
    1.52
    
    1.52
     arcilla
    1.52
    Activations Density 0.019%

    No Known Activations