© 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. 21376
    Prev
    Next
    INDEX
    Explanations

    FILED, 知识, 创建, Ž

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

    This neuron is tuned to detect uppercase letters with non-ASCII diacritics (e.g. “Ž”).

    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
    ↵
    -3.28
    𝄆
    -2.95
     ſou
    -2.77
     北市
    -2.72
    餿
    -2.59
     посмотреть
    -2.48
     mesures
    -2.47
     unbelievably
    -2.36
     ブルー
    -2.34
     incredibly
    -2.33
    POSITIVE LOGITS
    ًا
    2.69
     This
    2.52
     Seem
    2.50
    hasilkan
    2.47
     \#
    2.45
     Looks
    2.44
     unangemess
    2.39
    鈇
    2.39
     If
    2.33
     kepada
    2.33
    Activations Density 0.004%

    No Known Activations