© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4493
    Prev
    Next
    INDEX
    Explanations

    mathematics and science subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    afone
    1.18
    {$
    1.13
    邀请
    1.04
    |[
    0.99
    只需
    0.99
    縈
    0.98
    ваш
    0.97
     Either
    0.95
    ([(
    0.95
    后者
    0.94
    POSITIVE LOGITS
    基本的な
    2.07
     basics
    2.03
     fundamentals
    2.03
     Fundamentals
    1.96
     exothermic
    1.92
    ändig
    1.89
     Basics
    1.87
    法則
    1.84
     UNITS
    1.83
     homeostasis
    1.79
    Activations Density 0.039%

    No Known Activations