© 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-16K
    7. 7828
    Prev
    Next
    INDEX
    Explanations

    electronic

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    リティ
    0.43
     AI
    0.40
     прадстаў
    0.40
    ীন
    0.39
     Menu
    0.38
    ศูนย์
    0.38
     명령어
    0.38
     Gloss
    0.38
     극
    0.38
     SMC
    0.37
    POSITIVE LOGITS
     electronic
    1.41
     Electronic
    1.38
    Electronic
    1.37
    electronic
    1.34
     электрон
    1.33
     ELECTRON
    1.30
     elektron
    1.27
     electronics
    1.23
    电子
    1.23
    電子
    1.23
    Activations Density 0.068%

    No Known Activations