© 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. 22751
    Prev
    Next
    INDEX
    Explanations

    foreign languages and proper nouns on Wikipedia

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

    The neuron detects demonym or nationality adjective tokens (e.g. suffixes like “-ano,” “-eño/-eña,” “-ese,” “-ais/-aise,” etc.).

    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
    犼
    -2.06
    赑
    -2.00
    が付いて
    -1.89
    苼
    -1.89
    ⬮
    -1.88
    鉿
    -1.82
    寕
    -1.78
    Украина
    -1.77
     své
    -1.77
    偁
    -1.75
    POSITIVE LOGITS
     rapida
    1.77
    (
    1.72
     });
    1.64
    躥
    1.62
     devia
    1.62
    en
    1.56
     ぼ
    1.56
     claiming
    1.53
     centrif
    1.51
     pratica
    1.51
    Activations Density 0.013%

    No Known Activations