© 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. 117500
    Prev
    Next
    INDEX
    Explanations

    Plaintiff versus

    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
    Ubuntu
    -0.06
     कांटे
    -0.06
    🍣
    -0.06
     ব্যক্তিকে
    -0.06
    zeka
    -0.06
    葬
    -0.06
    গ্ত
    -0.05
     বাহিরে
    -0.05
     orijinal
    -0.05
     Amendment
    -0.05
    POSITIVE LOGITS
     these
    0.08
    回來
    0.07
    ↵
    0.06
    Estas
    0.06
     his
    0.06
     questi
    0.06
     new
    0.06
     reliable
    0.06
     اغلب
    0.06
     даже
    0.06
    Activations Density 0.004%

    No Known Activations