© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51792
    Prev
    Next
    INDEX
    Explanations

    names starting with Marc

    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_65k_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
    雉
    0.41
    তাবাদ
    0.39
    dong
    0.39
     పా
    0.37
    चों
    0.37
    尒
    0.37
     động
    0.37
    πά
    0.37
     Dons
    0.36
    ዐ
    0.36
    POSITIVE LOGITS
    Antoine
    0.46
    Marc
    0.43
    本书
    0.43
    inko
    0.43
     Antoine
    0.38
    INK
    0.38
    本書
    0.38
    ographic
    0.37
     Algebraic
    0.37
    Amount
    0.36
    Activations Density 0.004%

    No Known Activations