© 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. 16676
    Prev
    Next
    INDEX
    Explanations

    professional sports debut

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

    The neuron activates on mentions of an athlete’s career “debut,” especially the phrase “made his/her … debut” often paired with a date.

    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
    共同
    -1.09
    <bos>
    -1.07
     һәм
    -1.06
     annually
    -0.95
    X
    -0.93
     $
    -0.90
    多年
    -0.90
    M
    -0.90
    colgroup
    -0.89
     czyli
    -0.89
    POSITIVE LOGITS
     tester
    1.16
     on
    1.16
     baptism
    1.10
    tester
    1.04
    を果た
    1.03
     debut
    1.02
    homonymie
    0.98
     esperado
    0.95
    debut
    0.94
    fiés
    0.93
    Activations Density 0.058%

    No Known Activations