© 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. 139761
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    lexer, scanner, tokenizer

    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
    ?
    0.54
     I
    0.50
     {
    0.47
    !
    0.45
     Navidad
    0.45
    мал
    0.45
     Bachelor
    0.44
     Puerto
    0.43
     :
    0.43
     Henry
    0.43
    POSITIVE LOGITS
     mettent
    0.54
    érm
    0.51
    り
    0.48
     fornisce
    0.48
    ო
    0.47
    濾
    0.47
     molécules
    0.47
    麥
    0.47
    ಿಂದ
    0.46
     ド
    0.46
    Activations Density 0.000%

    No Known Activations