© 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. 36254
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    public class

    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
    ループ
    0.43
    誨
    0.41
     Collecting
    0.38
    パワ
    0.38
    学
    0.38
     உள்ளார்
    0.38
    Correction
    0.37
    P
    0.37
    books
    0.37
     طويلة
    0.37
    POSITIVE LOGITS
     izgled
    0.41
     tokenize
    0.41
    avak
    0.40
     vendas
    0.40
    لاقي
    0.39
    imwrite
    0.38
     fumar
    0.38
     bhavanti
    0.37
     hava
    0.37
    твра
    0.37
    Activations Density 0.000%

    No Known Activations