© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115987
    Prev
    Next
    INDEX
    Explanations

    Okada Physics

    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
    Negative Logits
     technologie
    -0.07
     Technologie
    -0.07
     Technology
    -0.07
     hätte
    -0.07
    overy
    -0.07
     yöntem
    -0.07
     technology
    -0.07
     Agriculture
    -0.06
     технологи
    -0.06
    二氧化
    -0.06
    POSITIVE LOGITS
     frequently
    0.06
    并发
    0.06
     roar
    0.06
     clotting
    0.06
     roaring
    0.06
    rl
    0.05
     ঈদের
    0.05
    airo
    0.05
     homecoming
    0.05
     treats
    0.05
    Activations Density 0.015%

    No Known Activations