© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72945
    Prev
    Next
    INDEX
    Explanations

    names and Chinese characters

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

    The neuron detects capitalized identifiers and proper nouns—such as class or type names, author names, and scientific or product 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
    ↵
    -3.73
    は
    -3.45
    c
    -3.34
     ''
    -3.30
    t
    -3.05
    ii
    -3.02
    2
    -3.00
    3
    -3.00
    et
    -2.86
     {
    -2.78
    POSITIVE LOGITS
    雳
    3.06
    ):
    2.86
    鵟
    2.83
    鐿
    2.70
    利
    2.69
    朥
    2.67
    沨
    2.67
    镠
    2.61
    ꪔ
    2.61
    趼
    2.59
    Activations Density 0.019%

    No Known Activations