© 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. 120791
    Prev
    Next
    INDEX
    Explanations

    mammograms, judges, and questions

    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
     затем
    -0.06
    .
    -0.06
    ole
    -0.06
     سپس
    -0.06
    ówczas
    -0.06
    随后
    -0.06
     намере
    -0.06
     बेचने
    -0.06
     wówczas
    -0.06
     otra
    -0.06
    POSITIVE LOGITS
     they
    0.07
     jedan
    0.06
     หนึ่ง
    0.06
    及び
    0.06
     הם
    0.06
     ağır
    0.06
    まずは
    0.06
     및
    0.06
     ताजा
    0.06
     unusually
    0.06
    Activations Density 0.001%

    No Known Activations