© 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. 26338
    Prev
    Next
    INDEX
    Explanations

    client

    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
    刁
    0.42
     pellets
    0.39
     shutdown
    0.38
     चहल
    0.38
    jokes
    0.37
     chili
    0.37
    嫉
    0.37
    xel
    0.37
     sulfides
    0.37
    anges
    0.36
    POSITIVE LOGITS
     ८
    0.43
     Cro
    0.41
     кро
    0.41
    PHOT
    0.39
     CRO
    0.38
    供应
    0.38
     المرأة
    0.38
     σαν
    0.37
     Hackett
    0.37
    STA
    0.37
    Activations Density 0.000%

    No Known Activations