© 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. 41-GEMMASCOPE-2-RES-262K
    7. 6809
    Prev
    Next
    INDEX
    Explanations

    drawing shapes, sorting, locks, numbers, ascii, splitting, rooms, pi

    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
     vértice
    0.32
    PERATURE
    0.30
     posición
    0.30
     funções
    0.30
     ângulo
    0.30
    醂
    0.30
    ោម
    0.29
    cutaneous
    0.29
    บคุม
    0.29
     combinación
    0.29
    POSITIVE LOGITS
    _
    0.37
     to
    0.37
    in
    0.35
    to
    0.34
    -
    0.34
    ed
    0.33
    To
    0.33
    0
    0.32
    In
    0.32
    1
    0.32
    Activations Density 0.049%

    No Known Activations