© 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. 41-GEMMASCOPE-2-RES-262K
    7. 34838
    Prev
    Next
    INDEX
    Explanations

    background image, frames, electrostatic equilibrium

    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_all/layer_41_width_262k_l0_big
    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
     books
    0.57
     libri
    0.50
     book
    0.50
     Bücher
    0.48
     livro
    0.46
     libros
    0.46
     livros
    0.46
     책
    0.45
     книги
    0.45
     libro
    0.45
    POSITIVE LOGITS
    BGR
    0.42
     backgroundImage
    0.39
    दियों
    0.39
    ﺛ
    0.39
    bres
    0.38
    破碎
    0.36
    bg
    0.36
    腌
    0.35
    ∋
    0.35
     Garo
    0.35
    Activations Density 0.011%

    No Known Activations