© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98724
    Prev
    Next
    INDEX
    Explanations

    non-english characters and brands

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

    This neuron flags individual non-Latin script characters (e.g. Hebrew, Arabic, Cyrillic) in text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    in
    -3.33
    us
    -3.23
    h
    -2.97
     exquisitely
    -2.86
    s
    -2.77
    ’，
    -2.69
    With
    -2.58
    re
    -2.58
     perplexing
    -2.56
    眼下
    -2.55
    POSITIVE LOGITS
    馀
    2.59
     akus
    2.59
     EVEN
    2.53
    鰱
    2.45
     somewhat
    2.41
     câmera
    2.38
     vertik
    2.38
    
    2.34
    putting
    2.34
    completely
    2.34
    Activations Density 0.000%

    No Known Activations