© 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. 215476
    Prev
    Next
    INDEX
    Explanations

    gender expression and states

    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
     Çok
    0.42
    女朋友
    0.38
     Ç
    0.38
     endless
    0.37
    adiyah
    0.36
    Ç
    0.36
    ﺝ
    0.35
    bolinks
    0.35
    createServer
    0.34
    ナソニック
    0.34
    POSITIVE LOGITS
    zie
    0.40
    šem
    0.37
     ряда
    0.37
    Aware
    0.37
    izate
    0.36
     зрения
    0.35
     पीड़ित
    0.35
    ഘ
    0.35
    ized
    0.35
    otope
    0.35
    Activations Density 0.000%

    No Known Activations