© 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. 47237
    Prev
    Next
    INDEX
    Explanations

    race completion and positions

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

    The neuron strongly activates on words and numbers describing race outcomes—especially phrasing around crossing the finish line and position ranks (e.g. “cross,” “finish,” “first,” “ten positions”).

    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
    ға
    -0.88
    のお知らせ
    -0.79
    usun
    -0.77
     Maje
    -0.76
     roadmap
    -0.75
    clairage
    -0.73
     starting
    -0.73
    ylated
    -0.72
    ่อย
    -0.70
    iffen
    -0.68
    POSITIVE LOGITS
     crossing
    2.50
     crossed
    2.25
    Crossing
    2.09
     finish
    2.06
    crossing
    2.02
     Crossing
    1.89
     crossings
    1.88
    crossed
    1.88
     crosses
    1.82
    Finish
    1.77
    Activations Density 0.018%

    No Known Activations