© 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. 35307
    Prev
    Next
    INDEX
    Explanations

    where

    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
    你需要
    0.38
     brauch
    0.37
     nodig
    0.36
    អំ
    0.36
    స్తారు
    0.36
     በኋላ
    0.36
     probably
    0.35
     glorified
    0.35
    }(-\
    0.35
    indir
    0.34
    POSITIVE LOGITS
     where
    2.08
     wherever
    2.05
     где
    1.88
     whenever
    1.86
    where
    1.84
     donde
    1.77
     Where
    1.74
     Wherever
    1.72
    whenever
    1.72
    Where
    1.70
    Activations Density 0.001%

    No Known Activations