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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9624
    Prev
    Next
    INDEX
    Explanations

    Leonardo DiCaprio

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

    This neuron fires on Chinese (CJK) text tokens, marking passages written in Chinese.

    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
    .
    -3.80
     aña
    -2.27
     comenz
    -2.22
     but
    -2.20
     aparentemente
    -2.19
     econó
    -2.14
    man
    -2.13
     impresionante
    -2.11
     rám
    -2.11
    not
    -2.11
    POSITIVE LOGITS
    嚳
    2.73
    肏
    2.67
    儅
    2.59
    糴
    2.58
    ㈪
    2.42
     Sociale
    2.42
     astuces
    2.41
    蹀
    2.39
    BITDA
    2.39
     you
    2.39
    Activations Density 0.001%

    No Known Activations