© 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. 40-GEMMASCOPE-2-RES-262K
    7. 24251
    Prev
    Next
    INDEX
    Explanations

    Section number

    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_40_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
     ಇದ್ದ
    0.48
     بتساوي
    0.46
    ⌔
    0.45
     индекс
    0.45
    /).
    0.44
     ceea
    0.44
    setwd
    0.44
    codewords
    0.44
    idcoin
    0.44
    悅
    0.44
    POSITIVE LOGITS
     Section
    0.84
     section
    0.80
    Section
    0.78
     sections
    0.62
    section
    0.62
     §
    0.61
     Chapter
    0.61
    Sections
    0.60
     सेक्शन
    0.54
     Sections
    0.54
    Activations Density 0.003%

    No Known Activations