© 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. 208297
    Prev
    Next
    INDEX
    Explanations

    old trees wood garden

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

    gathering, invoking, nature, historical, calculus

    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
    晰
    0.45
    বঙ্গের
    0.45
     প্রক
    0.44
    '))->
    0.44
     জনসংখ্যার
    0.43
    క్షణ
    0.43
     د
    0.42
    ».
    0.42
     dẫn
    0.42
     ஏனெ
    0.42
    POSITIVE LOGITS
     convening
    0.53
    summon
    0.52
     summoning
    0.51
    ﺭ
    0.51
     janvier
    0.50
    sz
    0.47
    '
    0.46
    ANIEL
    0.45
     summoned
    0.45
     nowy
    0.45
    Activations Density 0.000%

    No Known Activations