© 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. 120787
    Prev
    Next
    INDEX
    Explanations

    David Jones executives, senior executives

    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
    这两
    -0.07
     serveur
    -0.06
     two
    -0.06
     особливо
    -0.06
     особенно
    -0.06
     other
    -0.06
     menyelesaikan
    -0.06
     শুনানি
    -0.06
     ㅜ
    -0.06
     especially
    -0.06
    POSITIVE LOGITS
     design
    0.08
     디자인
    0.07
     дизайнер
    0.07
    デザイン
    0.07
     enhancers
    0.06
     дизайн
    0.06
     dili
    0.06
     consciousness
    0.06
    设计
    0.06
    意識
    0.06
    Activations Density 0.027%

    No Known Activations