© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34422
    Prev
    Next
    INDEX
    Explanations

    . convert or resize

    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_40_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
     Trump
    0.41
     Cars
    0.35
    롱
    0.35
    モード
    0.35
    putation
    0.34
    령
    0.34
    ruff
    0.34
     Bush
    0.34
     Nixon
    0.34
     ateş
    0.34
    POSITIVE LOGITS
    萫
    0.42
     surf
    0.38
    Résumé
    0.37
    明治
    0.37
    鳧
    0.37
     خاک
    0.36
    ezas
    0.36
     ఎమ్
    0.35
    樫
    0.35
    ellidos
    0.35
    Activations Density 0.000%

    No Known Activations