© 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. 106226
    Prev
    Next
    INDEX
    Explanations

    religious and legal decisions

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

    The neuron fires on words naming religious identities or sects (e.g. “Muslim,” “Buddhist,” “Islamic,” “Shia”).

    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
     Joint
    -0.92
    Joint
    -0.88
     joint
    -0.87
     Cottage
    -0.84
    elos
    -0.81
    joint
    -0.78
    ंत्र
    -0.69
    ɒ
    -0.69
     κα
    -0.67
    brium
    -0.66
    POSITIVE LOGITS
     personal
    1.19
     divorce
    1.18
     Divorce
    1.16
    Divorce
    1.15
    Personal
    1.12
     Personal
    1.02
     PERSONAL
    0.99
    personal
    0.98
    PERSONAL
    0.94
     tala
    0.91
    Activations Density 0.013%

    No Known Activations