© 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-65K
    7. 56310
    Prev
    Next
    INDEX
    Explanations

    calculus optimization and sales

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    squared
    0.46
     школ
    0.45
    associated
    0.41
    ී
    0.41
    リード
    0.38
    transformed
    0.37
     अप्रैल
    0.37
    approximately
    0.37
     ምስ
    0.37
     encore
    0.36
    POSITIVE LOGITS
    로나
    0.39
    もし
    0.38
     Dying
    0.37
     tut
    0.35
     burgl
    0.35
    рень
    0.35
    ↯
    0.34
    ổng
    0.34
    एमपी
    0.34
     ввод
    0.33
    Activations Density 0.003%

    No Known Activations