© 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. 103743
    Prev
    Next
    INDEX
    Explanations

    Attractive Metro-style interface

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

    ways of writing

    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
    า
    0.52
    dna
    0.51
    division
    0.50
    really
    0.49
     площа
    0.48
    do
    0.47
    dre
    0.47
     ал
    0.47
    hydroxyl
    0.47
    тр
    0.47
    POSITIVE LOGITS
     TikTok
    0.49
     Maternal
    0.46
    释
    0.46
    Synced
    0.45
    间隔
    0.45
     interval
    0.44
     Incredible
    0.44
    自带
    0.44
    航班
    0.44
    лях
    0.44
    Activations Density 0.001%

    No Known Activations