© 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. 127826
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—especially integers and decimal numbers—in the text.

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

    binary and mathematical terms

    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
     final
    -0.90
    之道
    -0.88
     sviluppo
    -0.84
     experience
    -0.84
     how
    -0.84
    感じる
    -0.83
     저장
    -0.83
    vula
    -0.82
     keo
    -0.81
     finish
    -0.81
    POSITIVE LOGITS
    BOOLEAN
    1.02
     اکنون
    1.01
     Jornal
    0.98
    Iné
    0.98
     maintenant
    0.96
    SetBool
    0.96
    BorderFactory
    0.95
     лютого
    0.95
    TURE
    0.93
    fjspx
    0.93
    Activations Density 0.010%

    No Known Activations