© 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. 119588
    Prev
    Next
    INDEX
    Explanations

    HT patients

    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
       
    -0.06
     দৃষ্ট
    -0.06
     auswählen
    -0.06
     this
    -0.06
     আপনারা
    -0.06
    基层
    -0.05
     रिवाइज
    -0.05
     Krä
    -0.05
     revisions
    -0.05
    चान
    -0.05
    POSITIVE LOGITS
     者
    0.07
    ྦ
    0.06
     všet
    0.06
     কেন
    0.06
     আন্তর্জাতিক
    0.06
     व्यक्तियों
    0.06
     trayectoria
    0.06
    ၌
    0.06
    ZN
    0.06
    conditional
    0.06
    Activations Density 0.023%

    No Known Activations