© 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. 220924
    Prev
    Next
    INDEX
    Explanations

    effective dates and conditions

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

    connecting or separating concepts

    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
     создал
    0.46
    蠵
    0.44
    breast
    0.43
    期間
    0.43
    ಿದ್ದಾನೆ
    0.41
     创建
    0.40
    atalog
    0.40
    ostiene
    0.40
    率为
    0.39
    🏵
    0.39
    POSITIVE LOGITS
     easily
    0.52
    തര
    0.50
     audiovisual
    0.49
     народов
    0.49
     offspring
    0.49
     чрезвы
    0.48
     aero
    0.48
     esoteric
    0.48
    スー
    0.47
    อะ
    0.47
    Activations Density 0.001%

    No Known Activations