© 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. 129083
    Prev
    Next
    INDEX
    Explanations

    Chinese names, places, and terms

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

    The neuron is triggered by tokens containing non‐ASCII or non‐Latin characters (e.g. Chinese ideographs, Cyrillic letters, or Latin letters with diacritics).

    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
     он
    -2.14
    </h4>
    -1.89
    鈇
    -1.89
    '
    -1.89
    }{
    -1.88
    {
    -1.84
     jį
    -1.84
    -
    -1.83
     shove
    -1.81
    She
    -1.76
    POSITIVE LOGITS
    呖
    2.58
    踽
    2.44
    蓠
    2.38
    蹀
    2.38
    鹟
    2.33
     ícones
    2.28
    
    2.27
    臯
    2.27
    鲥
    2.23
    焢
    2.22
    Activations Density 0.034%

    No Known Activations