© 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. 117580
    Prev
    Next
    INDEX
    Explanations

    uric acid, oxidase, constitutive

    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
     Hello
    -0.06
     வாழ்க்க
    -0.06
     health
    -0.06
    ப்பிட
    -0.06
     binding
    -0.06
    勉
    -0.06
     tubercul
    -0.06
     monumental
    -0.06
     ആരോഗ്യ
    -0.06
     hello
    -0.05
    POSITIVE LOGITS
     allein
    0.07
     людей
    0.06
     forskjellige
    0.06
    钛
    0.06
    🛁
    0.06
    争议
    0.06
     สูตร
    0.06
     நவீன
    0.06
     ቀለም
    0.06
    数据
    0.06
    Activations Density 0.003%

    No Known Activations