© 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. 127504
    Prev
    Next
    INDEX
    Explanations

    list item separators

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

    The neuron fires on tokens containing Chinese (CJK) characters.

    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
     it
    -2.28
    \
    -2.11
    %;
    -1.99
    ﴾
    -1.94
    It
    -1.91
    }(
    -1.86
    :])
    -1.78
     However
    -1.78
    ........
    -1.73
    .......
    -1.73
    POSITIVE LOGITS
     nació
    1.96
    뻣
    1.77
    ܆
    1.77
     mármol
    1.75
    ギュラー
    1.73
     trám
    1.72
     verschillende
    1.72
     zrobić
    1.71
     italiens
    1.71
     possono
    1.70
    Activations Density 0.001%

    No Known Activations