© 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. 172231
    Prev
    Next
    INDEX
    Explanations

    your outfit, organizations

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

    multi-lingual 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
    Not in Any Lists

    No Comments

    Negative Logits
    젼
    0.51
    лена
    0.49
    ஜித்
    0.48
    fand
    0.48
    ция
    0.47
     रहीम
    0.45
     simmer
    0.45
    intosh
    0.45
    sb
    0.44
    aio
    0.44
    POSITIVE LOGITS
     跟
    0.57
     thuận
    0.54
     cheerfully
    0.49
     nuovi
    0.48
     dưỡng
    0.48
     hè
    0.46
    తో
    0.46
     ,[
    0.45
     ወደ
    0.45
    épaisseur
    0.45
    Activations Density 0.001%

    No Known Activations