© 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. 10-GEMMASCOPE-RES-131K
    7. 98772
    Prev
    Next
    INDEX
    Explanations

    participate in

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

    The neuron detects occurrences of “participate” (and its variants like “participant,” “participation,” “participating”), i.e. references to taking part in something.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     they
    -2.25
     &
    -2.02
    ’
    -1.91
    ículas
    -1.90
    '
    -1.84
     —
    -1.80
     Unidades
    -1.78
     that
    -1.77
    操作
    -1.77
     is
    -1.77
    POSITIVE LOGITS
    躂
    2.47
    Плюсы
    2.06
    particip
    2.00
    優れた
    1.91
    Преимущества
    1.87
    Partici
    1.87
     participate
    1.81
     PARTICIP
    1.79
    Жит
    1.79
    過的
    1.77
    Activations Density 0.054%

    No Known Activations