© 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. 100308
    Prev
    Next
    INDEX
    Explanations

    lawyer in legal citations

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

    the presence of non-Latin characters (i.e. tokens from scripts like Hebrew, Arabic, Thai, Cyrillic, etc.)

    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
    0
    -3.36
     européens
    -2.59
    It
    -2.55
     kematian
    -2.53
     parution
    -2.50
    футболка
    -2.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -2.28
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -2.28
    、【
    -2.27
    Переваги
    -2.20
    POSITIVE LOGITS
    罴
    2.73
    尨
    2.72
    蕺
    2.59
    ⸢
    2.48
    da
    2.44
    氿
    2.39
    鼍
    2.23
     ทำ
    2.23
    ౭
    2.19
    僦
    2.19
    Activations Density 0.001%

    No Known Activations