© 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. 8945
    Prev
    Next
    INDEX
    Explanations

    language fragments or word endings

    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
     a
    0.41
     The
    0.39
     only
    0.38
     two
    0.35
     Only
    0.34
     since
    0.33
     four
    0.33
     Two
    0.33
     as
    0.33
     cannot
    0.33
    POSITIVE LOGITS
    انات
    0.37
    签署
    0.35
    ارات
    0.33
     ويكيپيديا
    0.33
    arlı
    0.32
    艳
    0.31
    لمات
    0.31
    عات
    0.31
    uski
    0.30
    cesz
    0.30
    Activations Density 0.001%

    No Known Activations