© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118331
    Prev
    Next
    INDEX
    Explanations

    programming language versions (ES6, C++11, C#)

    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
    บน
    -0.06
     верхней
    -0.06
    pf
    -0.06
    лар
    -0.05
     Arist
    -0.05
     trước
    -0.05
    COM
    -0.05
    uers
    -0.05
     там
    -0.05
    embers
    -0.05
    POSITIVE LOGITS
     gall
    0.06
    亮点
    0.06
     ہماری
    0.06
    もう少し
    0.06
     Schwerpunkt
    0.06
     закончи
    0.06
    差距
    0.06
    explique
    0.06
    実現
    0.06
    ひとつ
    0.06
    Activations Density 0.003%

    No Known Activations