© 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. 57749
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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
     aboard
    0.75
     เรือ
    0.71
     кораб
    0.67
     ships
    0.66
     onboard
    0.66
     bateau
    0.64
    舰队
    0.64
    ⛵
    0.64
     warships
    0.63
    🛳
    0.63
    POSITIVE LOGITS
    class
    0.47
     training
    0.45
    Training
    0.44
     herself
    0.43
     Miscellaneous
    0.40
    Class
    0.39
    ctomy
    0.39
    Miscellaneous
    0.39
     survey
    0.38
     Training
    0.38
    Activations Density 0.002%

    No Known Activations