© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116478
    Prev
    Next
    INDEX
    Explanations

    static class/module/object declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     giỏi
    -0.06
     முன்னோ
    -0.06
     হউক
    -0.06
     istr
    -0.06
     osv
    -0.06
     suyo
    -0.06
     یې
    -0.06
     शिक्षित
    -0.06
     первым
    -0.06
    ricting
    -0.05
    POSITIVE LOGITS
     with
    0.07
    定義
    0.06
     accordance
    0.06
    ឧបករណ៍
    0.06
     microbiology
    0.06
     according
    0.06
     increments
    0.06
     কাব্য
    0.06
     nagyon
    0.06
     desesper
    0.06
    Activations Density 0.003%

    No Known Activations