© 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. 211834
    Prev
    Next
    INDEX
    Explanations

    programs, video, display, means

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

    centering, including, display, playground

    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
    Negative Logits
     yako
    0.55
     －
    0.47
     رہے۔
    0.47
     taint
    0.45
     unharmed
    0.45
    
    0.45
     libid
    0.44
     revolutionized
    0.44
    ーーーー
    0.43
    ⸝
    0.42
    POSITIVE LOGITS
     inklusive
    0.47
    na
    0.46
    iflor
    0.46
    攏
    0.46
     Playground
    0.44
     Display
    0.44
    ディスプレイ
    0.44
    eler
    0.43
    ចែក
    0.43
    set
    0.43
    Activations Density 0.001%

    No Known Activations