© 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. 119212
    Prev
    Next
    INDEX
    Explanations

    PWN

    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
    他也
    -0.06
     aswell
    -0.06
     понял
    -0.06
     مانند
    -0.06
    ঙ্ক
    -0.06
     semelhantes
    -0.06
    iele
    -0.06
     גם
    -0.06
     நட்ப
    -0.06
     lebih
    -0.05
    POSITIVE LOGITS
     інформа
    0.07
     আমার
    0.06
    Е
    0.06
     আসছেন
    0.06
     আপনার
    0.06
     könnten
    0.06
    获得
    0.06
     podrían
    0.06
     ejempl
    0.06
    *****",
    0.06
    Activations Density 0.001%

    No Known Activations