© 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. 61846
    Prev
    Next
    INDEX
    Explanations

    specific non-English words

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

    google cloud

    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
     апо
    0.45
     grandeza
    0.45
     Дже
    0.44
     Ро
    0.43
     ഷ
    0.43
     serii
    0.43
     单位
    0.42
     Zentrum
    0.42
     eşit
    0.42
     SQLAlchemy
    0.42
    POSITIVE LOGITS
    ਿਰ
    0.48
    HAM
    0.45
    केवल
    0.44
    僱
    0.44
    GOOGLE
    0.43
    ಶ್ಚ
    0.43
    雞
    0.43
    anées
    0.42
    श्च
    0.42
    وص
    0.42
    Activations Density 0.000%

    No Known Activations