© 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. 72175
    Prev
    Next
    INDEX
    Explanations

    Archie, Holo, Norma, Tari

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

    This neuron responds whenever a rare proper noun or named entity token appears (e.g. “Archie,” “Holo,” “Norma,” etc.).

    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
    鸶
    -2.97
    ."
    -2.89
     помогает
    -2.44
    蚡
    -2.44
    蟥
    -2.31
     поможет
    -2.27
    。
    -2.19
     März
    -2.17
    ми
    -2.13
    that
    -2.11
    POSITIVE LOGITS
    自己
    2.56
    真的
    2.38
    籏
    2.30
    会
    2.30
    красивые
    2.28
    ’，
    2.23
    就
    2.17
    絝
    2.16
    丏
    2.14
    想
    2.13
    Activations Density 0.003%

    No Known Activations