© 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. 40-GEMMASCOPE-2-RES-262K
    7. 796
    Prev
    Next
    INDEX
    Explanations

    world, life, days, titles

    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
    Negative Logits
    开发的
    0.35
     dell
    0.33
    তীশ
    0.32
     Develop
    0.32
     walnuts
    0.31
    Develop
    0.31
     rookies
    0.31
    éries
    0.30
     nuts
    0.30
     ${_
    0.29
    POSITIVE LOGITS
    orth
    0.37
    currency
    0.37
     செய்து
    0.37
     করার
    0.36
     करून
    0.36
     ചെയ്യുന്നു
    0.35
     करता
    0.35
    をして
    0.35
     fazendo
    0.35
     currency
    0.34
    Activations Density 0.000%

    No Known Activations