© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21420
    Prev
    Next
    INDEX
    Explanations

    legal and programming assignments

    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
    Negative Logits
     chemist
    0.44
    duire
    0.43
    醪
    0.43
     coverings
    0.42
     decimals
    0.41
     capillaries
    0.40
     consecrated
    0.40
    ironolactone
    0.39
    塗
    0.39
     filtrate
    0.39
    POSITIVE LOGITS
     вза
    0.42
     तेलंगाना
    0.41
     сред
    0.41
    ทะเล
    0.40
    Qual
    0.40
     திரு
    0.38
     Freund
    0.38
     śred
    0.38
     시민
    0.37
    Lua
    0.37
    Activations Density 0.000%

    No Known Activations