© 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. 166581
    Prev
    Next
    INDEX
    Explanations

    thanks and prices

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

    carrying, clutching, following, discovers

    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
     орга
    0.50
    playback
    0.49
     classed
    0.48
     tutors
    0.47
    LONG
    0.47
    Ж
    0.46
    江戸
    0.45
    虎
    0.45
     ад
    0.44
    Бе
    0.44
    POSITIVE LOGITS
     Спасибо
    0.57
     спасибо
    0.52
    谢谢
    0.49
     Thank
    0.44
     Marketplace
    0.44
    il
    0.43
    பட்ச
    0.43
    葡萄酒
    0.43
     얼마나
    0.42
    适用
    0.41
    Activations Density 0.001%

    No Known Activations