© 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. 127730
    Prev
    Next
    INDEX
    Explanations

    The neuron principally fires on numeric tokens (i.e. numbers or numeric literals) in the text.

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

    brightness

    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
     Hira
    -0.79
     če
    -0.77
     ситуации
    -0.74
     Insgesamt
    -0.74
     još
    -0.74
    getAction
    -0.73
     कहते
    -0.71
    jähriger
    -0.71
    enuto
    -0.70
     UITableViewCell
    -0.69
    POSITIVE LOGITS
    本人
    0.79
    достатки
    0.77
     reinigen
    0.75
    کنندگان
    0.75
     Reinforcement
    0.75
    *>(
    0.75
    после
    0.74
    timos
    0.73
     alene
    0.73
     varier
    0.72
    Activations Density 0.012%

    No Known Activations