© 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. 25134
    Prev
    Next
    INDEX
    Explanations

    code punctuation and operators

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

    The neuron responds to numeric literals (i.e. tokens consisting of numbers).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    kosť
    -0.89
    してほしい
    -0.88
     îmb
    -0.86
    Canto
    -0.85
    níků
    -0.84
    drá
    -0.84
     potrivit
    -0.83
     animado
    -0.81
     înainte
    -0.79
     pregă
    -0.79
    POSITIVE LOGITS
     remaining
    0.91
    它
    0.90
    remaining
    0.89
     PIN
    0.88
     والذي
    0.88
     IM
    0.85
    Remaining
    0.85
     DONE
    0.85
     هل
    0.84
     $^{\
    0.83
    Activations Density 0.005%

    No Known Activations