© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8423
    Prev
    Next
    INDEX
    Explanations

    describing information or identification

    np_acts-logits-general · gemini-2.5-flash-lite

    lists and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     andere
    0.36
    的
    0.35
     Japan
    0.35
    exists
    0.35
    are
    0.34
    ၏
    0.34
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
    ////////////////
    0.34
    oree
    0.34
    且
    0.34
    POSITIVE LOGITS
     우리는
    0.99
     이는
    0.93
    これは
    0.90
     저는
    0.85
    這是
    0.84
     これは
    0.84
     ਤੁਸੀਂ
    0.82
     we
    0.79
     यह
    0.77
    我就
    0.77
    Activations Density 1.188%

    No Known Activations