© 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. 34-GEMMASCOPE-RES-131K
    7. 3454
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron is highly responsive to numeric tokens and expressions (digits and number words).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     meni
    -0.92
     kabar
    -0.90
     lahan
    -0.90
     даже
    -0.90
     }</
    -0.86
    radan
    -0.84
     araba
    -0.84
     desember
    -0.83
     surg
    -0.82
     kropp
    -0.81
    POSITIVE LOGITS
     Beacons
    0.92
     持ち
    0.91
     PEST
    0.87
     GOtt
    0.87
     まとめ
    0.86
     chemic
    0.85
    があり
    0.84
    acja
    0.84
    扨
    0.84
    agerie
    0.82
    Activations Density 0.170%

    No Known Activations