© 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. 38547
    Prev
    Next
    INDEX
    Explanations

    creating and building in multiple languages

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

    This neuron responds to verb forms (inflected or participial) across languages.

    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
    鹛
    -2.73
    𓋼
    -2.38
    赑
    -2.20
    Отлич
    -1.84
    Leírás
    -1.84
    不得不说
    -1.82
    蹕
    -1.80
    
    -1.77
    ためには
    -1.77
    Excelente
    -1.74
    POSITIVE LOGITS
     he
    2.08
    o
    1.92
     Mitarbeitern
    1.86
     stránky
    1.77
     perfeita
    1.77
     a
    1.73
     Jugendliche
    1.70
    berfläche
    1.68
     skupiny
    1.67
     Does
    1.66
    Activations Density 0.011%

    No Known Activations