© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198527
    Prev
    Next
    INDEX
    Explanations

    multilingual foreign words

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

    here's after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     출
    0.46
     области
    0.45
     APP
    0.45
     һәм
    0.44
     влас
    0.43
     строительства
    0.43
    станов
    0.42
    новь
    0.41
     광
    0.41
    ному
    0.41
    POSITIVE LOGITS
     gode
    0.62
     kompl
    0.55
    如果
    0.52
    Anche
    0.52
     lauf
    0.51
     også
    0.50
     दही
    0.50
    捭
    0.50
     bakter
    0.50
     kiles
    0.49
    Activations Density 0.000%

    No Known Activations