© 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. 22481
    Prev
    Next
    INDEX
    Explanations

    Marie Claire

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

    The neuron fires on occurrences of the proper name “Marie,” marking when that first name appears in entity or person names.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     they
    -2.53
    很少
    -2.45
     VERY
    -2.45
     เพราะ
    -2.33
    栳
    -2.31
     to
    -2.27
    "}}>
    -2.23
    真的是
    -2.20
    ING
    -2.11
    ).
    -2.06
    POSITIVE LOGITS
    ization
    3.14
    鹟
    2.86
    e
    2.78
     現貨
    2.69
    ться
    2.64
    趼
    2.64
    袿
    2.34
     unrelenting
    2.34
    蕺
    2.34
     unparalleled
    2.33
    Activations Density 0.002%

    No Known Activations