© 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. 94216
    Prev
    Next
    INDEX
    Explanations

    names of people and roles

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

    The neuron fires most strongly on proper names—especially personal names (actors, directors, characters)—in film‐ or movie‐description contexts.

    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
     synag
    -0.89
    solic
    -0.84
     AKT
    -0.76
    回戦
    -0.75
     OBE
    -0.74
     運動
    -0.73
     FIA
    -0.72
     Synagogue
    -0.72
    attr
    -0.71
     Kā
    -0.71
    POSITIVE LOGITS
     cavalry
    0.82
    gesellschaft
    0.77
    sendEmail
    0.74
     Rode
    0.73
    Wester
    0.73
    /~
    0.72
     лоша
    0.71
     Pilar
    0.71
     wagon
    0.71
    wester
    0.69
    Activations Density 0.017%

    No Known Activations