© 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. 128710
    Prev
    Next
    INDEX
    Explanations

    javascript code obfuscation

    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
     tendrás
    -0.06
    TECH
    -0.06
     журнала
    -0.06
    നായി
    -0.06
    াক
    -0.05
    ;
    -0.05
     teş
    -0.05
     royal
    -0.05
     Fault
    -0.05
    POSITIVE LOGITS
    根据
    0.06
     গাড়ি
    0.06
     whereas
    0.06
     meeste
    0.06
     单
    0.06
    還
    0.06
    ফটেন্যান্ট
    0.06
     ಸಾಧ್ಯ
    0.06
     uscita
    0.06
    এদিকে
    0.06
    Activations Density 0.001%

    No Known Activations