© 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. 31-GEMMASCOPE-2-RES-262K
    7. 127849
    Prev
    Next
    INDEX
    Explanations

    classes, Registration, complementary, DATE, lead

    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/layer_31_width_262k_l0_medium
    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
     Иногда
    0.51
    但
    0.48
     但
    0.46
     Cinderella
    0.46
    ую
    0.46
     utilisent
    0.46
    ర్స్
    0.46
    不仅
    0.44
    难以
    0.44
     Cologne
    0.43
    POSITIVE LOGITS
    $-
    0.41
     thereby
    0.39
     جناب
    0.38
     كانوا
    0.38
     linebreak
    0.38
     meaningless
    0.37
     sila
    0.36
    すなわち
    0.36
    gged
    0.36
     ندا
    0.35
    Activations Density 0.007%

    No Known Activations