© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    unions and state machines

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

    class definitions and imports

    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
    ﺩ
    0.46
     nick
    0.44
     setText
    0.44
    скоп
    0.42
    smoking
    0.42
     descansar
    0.42
    '=>'','
    0.42
    iveau
    0.41
     descanso
    0.41
    σκο
    0.41
    POSITIVE LOGITS
     கீழ
    0.45
    囯
    0.43
     Kampf
    0.42
    種類
    0.41
    叫
    0.40
     Proto
    0.40
     denominado
    0.40
     millennia
    0.39
     mistura
    0.39
    叫做
    0.39
    Activations Density 0.000%

    No Known Activations