© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8442
    Prev
    Next
    INDEX
    Explanations

    decompile or reverse engineer

    np_acts-logits-general · gemini-2.5-flash-lite

    swapFactorcaptureMethodFree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endonuclease
    0.55
     homologs
    0.52
    ertime
    0.51
    ровой
    0.49
     Акы
    0.48
    inia
    0.46
     preprocess
    0.45
    夷
    0.45
     subarrays
    0.44
     инструментов
    0.43
    POSITIVE LOGITS
    ↵
    0.64
    credits
    0.49
    3
    0.47
     cumpl
    0.45
     ريد
    0.44
     غير
    0.44
     دار
    0.43
    s
    0.43
     den
    0.43
    credit
    0.43
    Activations Density 0.000%

    No Known Activations