© 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. 30113
    Prev
    Next
    INDEX
    Explanations

    spot fixing and betting

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

    The neuron fires most on words signaling legal or disciplinary contexts (e.g. bans, crimes, injunctions, involvement in wrongdoing).

    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
     ppm
    -0.78
     MDA
    -0.77
    ppm
    -0.76
    🍪
    -0.75
    BSD
    -0.73
    marle
    -0.73
     расходы
    -0.70
     varanda
    -0.70
    actos
    -0.69
     getY
    -0.68
    POSITIVE LOGITS
     fixing
    1.43
     fix
    1.35
     betting
    1.32
    Fixing
    1.24
    fixing
    1.24
     Fixing
    1.24
     fixes
    1.23
     match
    1.20
     FIXED
    1.20
     fixed
    1.19
    Activations Density 0.012%

    No Known Activations