© 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. 22-GEMMASCOPE-RES-131K
    7. 127880
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on numeric tokens—years, percentages, statistics, and other figures.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    more ... than

    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
    Negative Logits
     particularly
    -0.91
     correcta
    -0.89
     материалы
    -0.89
    pendenti
    -0.88
    möglich
    -0.85
    ymmetry
    -0.84
    也能
    -0.84
     exacerbate
    -0.82
    igten
    -0.82
    stoel
    -0.82
    POSITIVE LOGITS
     traditional
    1.05
    fontFamily
    0.99
     other
    0.96
    同期
    0.95
     any
    0.93
     чёрный
    0.92
     тради
    0.90
    IANA
    0.88
     COMBIN
    0.88
    ילים
    0.88
    Activations Density 0.031%

    No Known Activations