© 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. 22738
    Prev
    Next
    INDEX
    Explanations

    Polish place names and currency

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

    This neuron activates on Polish diacritic characters—especially the letter “Ł” (and its lowercase “ł”)—in tokens.

    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
    橚
    -2.92
     russes
    -2.78
     rigue
    -2.77
    趼
    -2.75
    
    -2.67
    鹮
    -2.66
     femininas
    -2.64
    獁
    -2.58
     cikk
    -2.56
     моя
    -2.50
    POSITIVE LOGITS
    ł
    2.73
    
    2.64
    л
    2.63
    缡
    2.50
     машин
    2.50
    .”
    2.44
     granting
    2.42
     avec
    2.33
    のよう
    2.22
     rant
    2.17
    Activations Density 0.003%

    No Known Activations