© 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. 71186
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    multi-lingual negation and topic shifting

    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
    Negative Logits
    っ
    0.50
    ｃｍ
    0.49
    という
    0.47
    Riga
    0.47
    レ
    0.46
    の
    0.45
     ดังนั้น
    0.45
    ん
    0.45
    cra
    0.45
    りました
    0.45
    POSITIVE LOGITS
     dépour
    0.52
     not
    0.50
     tema
    0.50
     não
    0.46
     ikke
    0.46
     bukan
    0.45
     includ
    0.45
     عادی
    0.43
     ليس
    0.43
     nicht
    0.42
    Activations Density 0.000%

    No Known Activations