© 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. 71260
    Prev
    Next
    INDEX
    Explanations

    Protein Expression, determine if, dumpster

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

    likely due to

    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
     изначально
    0.46
     উদ
    0.46
     ಸ್ವ
    0.46
    IDField
    0.46
     行
    0.45
     Сте
    0.45
    📄
    0.45
    獾
    0.44
     যেখানে
    0.44
    👊
    0.44
    POSITIVE LOGITS
     frivol
    0.47
    وبت
    0.46
     a
    0.45
     motoring
    0.45
     stoff
    0.44
     naudoj
    0.44
     cuidados
    0.44
     konkur
    0.44
     poziom
    0.42
     obsol
    0.41
    Activations Density 0.002%

    No Known Activations