© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74819
    Prev
    Next
    INDEX
    Explanations

    words in various languages

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

    discussing words

    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
     Vikipedi
    0.56
    фесси
    0.55
    scraper
    0.55
    し
    0.55
     ministerial
    0.52
    ;',
    0.52
    שת
    0.51
    crawler
    0.50
    shoring
    0.50
    )?;
    0.49
    POSITIVE LOGITS
     слова
    0.63
     शब्द
    0.63
     woord
    0.62
     वर्ड
    0.59
    शब्द
    0.59
    words
    0.58
     WORD
    0.56
     शब्दों
    0.55
     Word
    0.54
    ك
    0.54
    Activations Density 0.003%

    No Known Activations