© 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. 244089
    Prev
    Next
    INDEX
    Explanations

    selection, request, therapy, gamers, cash, write

    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
     Вайлд
    0.54
    มอบ
    0.51
    меется
    0.48
    ற்புத
    0.45
    Cats
    0.44
    दम
    0.43
    rep
    0.43
    ์
    0.43
    टु
    0.42
     Такая
    0.42
    POSITIVE LOGITS
    ógy
    0.49
    百姓
    0.47
     غلام
    0.46
    ítása
    0.45
    ários
    0.44
     vụ
    0.44
     गरीब
    0.43
    后者
    0.43
     plunged
    0.43
    وري
    0.42
    Activations Density 0.001%

    No Known Activations