© 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. 45517
    Prev
    Next
    INDEX
    Explanations

    names and legal entities

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

    The neuron activates on numeric tokens (whole numbers and decimals).

    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
    鈇
    -2.28
     italiens
    -2.25
    梱
    -2.19
    gunaan
    -2.17
     炭
    -2.17
    鄲
    -2.14
     japonais
    -2.09
    ギュア
    -2.09
    
    -2.08
     juſ
    -2.06
    POSITIVE LOGITS
     has
    2.48
    $
    2.45
     to
    2.25
    {
    2.17
     
    2.16
     but
    2.11
     will
    2.08
     this
    2.05
    ar
    2.00
     using
    1.98
    Activations Density 0.020%

    No Known Activations