© 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. 45731
    Prev
    Next
    INDEX
    Explanations

    questions about existence or utility

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

    The neuron fires on numeric expressions (especially numbers, including decimals) in the text.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     peut
    -1.62
    ਗ਼
    -1.48
    ENED
    -1.41
     может
    -1.39
     THOMAS
    -1.37
    雠
    -1.34
    鸩
    -1.34
     парк
    -1.34
     μπορεί
    -1.34
     SECOND
    -1.34
    POSITIVE LOGITS
     usually
    2.16
     with
    2.11
     most
    2.02
     because
    1.97
     people
    1.91
     only
    1.91
     commonly
    1.78
     ostensibly
    1.70
     presumably
    1.70
     always
    1.70
    Activations Density 0.422%

    No Known Activations