© 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. 56877
    Prev
    Next
    INDEX
    Explanations

    data descriptions and code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ungu
    0.45
     다
    0.41
     Facebook
    0.41
     "¿
    0.39
     الإنترنت
    0.38
     Какие
    0.38
    ing
    0.37
     TEM
    0.37
     Social
    0.37
     WhatsApp
    0.37
    POSITIVE LOGITS
    榄
    0.44
     ceb
    0.39
    ंगामा
    0.39
    ໝ
    0.39
    বিত
    0.38
     кеңсе
    0.38
     اہلِ
    0.38
    شارة
    0.37
    !',
    0.37
     ама
    0.37
    Activations Density 4.611%

    No Known Activations