© 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. 83973
    Prev
    Next
    INDEX
    Explanations

    knowing for sure

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

    This neuron identifies numeric tokens (both integer and decimal) and its activation reflects the numeric value of the token.

    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
     boneca
    -1.59
    鉨
    -1.55
    
    -1.52
     rámci
    -1.48
     recenz
    -1.47
     alemán
    -1.45
     allí
    -1.44
     mundos
    -1.44
     frère
    -1.43
     tomto
    -1.43
    POSITIVE LOGITS
     that
    2.06
    [];
    1.61
    and
    1.60
     avendo
    1.59
    en
    1.55
    鲵
    1.49
    a
    1.48
    breviations
    1.47
    tså
    1.47
    le
    1.44
    Activations Density 0.008%

    No Known Activations