© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23529
    Prev
    Next
    INDEX
    Explanations

    solve problems

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

    solving problems

    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
    Not in Any Lists

    No Comments

    Negative Logits
    も
    0.59
     in
    0.55
     code
    0.55
    在
    0.53
     saff
    0.52
    部位
    0.52
    ដំណើរ
    0.50
    t
    0.49
     spread
    0.49
     recovery
    0.49
    POSITIVE LOGITS
     проблемы
    1.05
     problemas
    1.02
     проблеми
    1.01
     problemy
    1.01
     problèmes
    0.99
     problemi
    0.99
     проблему
    0.95
     problema
    0.94
     مشکلات
    0.93
     문제를
    0.93
    Activations Density 0.049%

    No Known Activations