© 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. 83240
    Prev
    Next
    INDEX
    Explanations

    drill bit

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

    NVIDIA search volume

    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
     الملف
    0.47
     ファイル
    0.46
     सेटिंग
    0.45
    コンピュータ
    0.44
    Ϫ
    0.43
     subdirectory
    0.43
     बर्फ
    0.42
     компьютера
    0.42
     कंप्यूटर
    0.41
    >*
    0.40
    POSITIVE LOGITS
     Cyclone
    0.40
     which
    0.39
     хотелось
    0.39
     રહ્યો
    0.39
     Eze
    0.38
     Hercules
    0.38
    cije
    0.38
     voglia
    0.38
     hoping
    0.37
    razio
    0.37
    Activations Density 0.000%

    No Known Activations