© 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. 118985
    Prev
    Next
    INDEX
    Explanations

    Richard III and plays

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

    The neuron chiefly activates on numeric tokens—especially years, dates, and other numbers—in the text.

    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
    Alexis
    -0.78
     suc
    -0.74
    reco
    -0.72
    pad
    -0.71
    estus
    -0.71
     subterrá
    -0.70
    لاه
    -0.69
    észetes
    -0.69
     reco
    -0.68
    uttosto
    -0.67
    POSITIVE LOGITS
     York
    1.30
     Richard
    1.03
    York
    0.96
     Yorkshire
    0.95
     Princes
    0.90
     york
    0.89
     YORK
    0.87
    Yorkshire
    0.85
    york
    0.84
    Richard
    0.83
    Activations Density 0.008%

    No Known Activations