© 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. 31-GEMMASCOPE-2-RES-262K
    7. 110092
    Prev
    Next
    INDEX
    Explanations

    lodging and sacrifices

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

    confidence, not arrogance

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insieme
    0.49
     together
    0.48
     Together
    0.47
    <0xCF>
    0.46
    amsfonts
    0.45
     insieme
    0.45
     وین
    0.45
    iflor
    0.44
    
    0.44
     Reproductive
    0.43
    POSITIVE LOGITS
    0.54
     étudi
    0.53
     अनुप
    0.49
     भाषा
    0.48
     STUD
    0.48
     ไฟล์
    0.47
    打电话
    0.47
     board
    0.46
     studs
    0.45
     wave
    0.44
    Activations Density 0.001%

    No Known Activations