© 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. 104793
    Prev
    Next
    INDEX
    Explanations

    citations and page numbers

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

    local economies, book

    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
     forment
    0.49
     golfer
    0.48
    otrexate
    0.48
    ẹ
    0.47
     mögliche
    0.46
     botão
    0.45
    ulfanyl
    0.45
    тник
    0.45
     elő
    0.44
     либо
    0.44
    POSITIVE LOGITS
    ž
    0.45
    綰
    0.42
     Juni
    0.41
     marches
    0.41
     Z
    0.40
    SS
    0.40
     Habs
    0.39
    liku
    0.39
     dances
    0.39
    Ş
    0.39
    Activations Density 0.001%

    No Known Activations