© 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. 187285
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and researchers

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

    research communities

    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
    。
    0.54
     попы
    0.49
    大全
    0.46
    ，
    0.46
     любой
    0.45
    仙
    0.44
     сразу
    0.44
    CD
    0.44
    魔
    0.42
     следу
    0.42
    POSITIVE LOGITS
     تحقی
    0.51
     linguistics
    0.49
     carbides
    0.48
     professeur
    0.47
     chercheurs
    0.46
     intellectuals
    0.46
     researches
    0.46
     alkalies
    0.46
     anthropologists
    0.44
     valour
    0.44
    Activations Density 0.001%

    No Known Activations