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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38485
    Prev
    Next
    INDEX
    Explanations

    punctuations and the text 'foreign' or 'warl'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ون
    0.54
    ু
    0.54
    (
    0.51
    도
    0.51
    ه
    0.50
    刪
    0.50
     было
    0.49
     könnt
    0.49
    ও
    0.48
    "
    0.48
    POSITIVE LOGITS
     to
    0.60
     is
    0.55
    पहरण
    0.46
    ritz
    0.46
     ļ
    0.46
    sodium
    0.45
    isAuthenticated
    0.44
    liquibase
    0.44
     peninsula
    0.44
     thoſe
    0.44
    Activations Density 0.003%

    No Known Activations