© 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. 47126
    Prev
    Next
    INDEX
    Explanations

    Persian history and rulers

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

    The neuron fires on capitalized named entities—proper names and titles.

    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
     preachers
    -0.77
     Elin
    -0.75
    Onion
    -0.73
     Elo
    -0.72
     Võ
    -0.71
    níka
    -0.71
     Duan
    -0.71
     Highlander
    -0.71
     mandibular
    -0.70
    TESTING
    -0.70
    POSITIVE LOGITS
    ̰
    0.94
     Cyrus
    0.81
     taller
    0.81
     Mazda
    0.78
     Darius
    0.77
     Iran
    0.77
     Boyce
    0.75
    Dad
    0.75
    fici
    0.73
     disc
    0.72
    Activations Density 0.024%

    No Known Activations