© 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. 30633
    Prev
    Next
    INDEX
    Explanations

    E, Ek, Equ, Ech prefixes

    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
    OCKET
    0.46
    highlight
    0.44
     Льво
    0.43
    思議
    0.43
    aleb
    0.42
     حالت
    0.42
    饪
    0.42
     highlight
    0.41
    ശാ
    0.41
    躏
    0.41
    POSITIVE LOGITS
     Equ
    0.53
     Ek
    0.48
     embal
    0.48
     ect
    0.47
     ek
    0.43
     Equitable
    0.41
     Ech
    0.39
     equ
    0.39
     Extracts
    0.38
     equi
    0.38
    Activations Density 0.002%

    No Known Activations