© 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. 4496
    Prev
    Next
    INDEX
    Explanations

    Jupyter Notebooks

    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
    gı
    0.43
    ड़े
    0.41
     WndProc
    0.40
    噉
    0.38
    इंड
    0.38
    ্টর
    0.37
    琥
    0.37
    TikTok
    0.37
    正确的
    0.37
    呉
    0.37
    POSITIVE LOGITS
     Notebook
    0.71
     notebook
    0.70
     노트북
    0.63
    Notebook
    0.60
     notebooks
    0.58
     ноутбу
    0.55
     laptop
    0.52
    笔记本
    0.51
    notebook
    0.50
     नोटबुक
    0.50
    Activations Density 0.005%

    No Known Activations