© 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. 116145
    Prev
    Next
    INDEX
    Explanations

    postoperative patients

    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
    simply
    -0.07
     où
    -0.07
    where
    -0.06
    when
    -0.06
     lorsque
    -0.06
     lorsqu
    -0.06
     anglès
    -0.06
     simplement
    -0.06
     لدى
    -0.06
     mentre
    -0.06
    POSITIVE LOGITS
     with
    0.07
    뭍
    0.06
     has
    0.06
    `
    0.06
    絶対
    0.06
    posts
    0.06
     decidedly
    0.06
     koń
    0.06
     might
    0.05
     van
    0.05
    Activations Density 0.010%

    No Known Activations