© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130686
    Prev
    Next
    INDEX
    Explanations

    django or Django

    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
     vaš
    -0.07
    आम
    -0.07
    ិក
    -0.06
     ваша
    -0.06
     YOUR
    -0.06
    ესი
    -0.06
     vaše
    -0.06
     درمیان
    -0.06
     一般
    -0.06
    你的
    -0.06
    POSITIVE LOGITS
    princip
    0.06
    Inser
    0.06
     one
    0.06
     vervolgens
    0.05
    Một
    0.05
     response
    0.05
     деятельность
    0.05
     одном
    0.05
     către
    0.05
     بدء
    0.05
    Activations Density 0.002%

    No Known Activations