© 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. 64785
    Prev
    Next
    INDEX
    Explanations

    Soviet Union leaders and dates

    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
     Право
    0.41
     戦
    0.40
     shopping
    0.39
    Kingdom
    0.39
     Midwestern
    0.38
     remix
    0.38
    Educational
    0.38
     快
    0.37
    講師
    0.37
     Industria
    0.37
    POSITIVE LOGITS
     ankle
    0.41
    newLine
    0.40
    ழு
    0.40
    ╚
    0.39
    orkel
    0.38
    ≥
    0.38
    мит
    0.37
    vertexBuffer
    0.36
    ปล่อย
    0.36
     abol
    0.36
    Activations Density 0.001%

    No Known Activations