© 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. 115924
    Prev
    Next
    INDEX
    Explanations

    articles and titles

    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
     eponymous
    -0.07
     meie
    -0.07
    在日本
    -0.07
     będzie
    -0.06
    一直
    -0.06
     언제
    -0.06
    每次
    -0.06
    常に
    -0.06
     denomin
    -0.06
     เรา
    -0.06
    POSITIVE LOGITS
     Which
    0.06
    qry
    0.06
    方面的
    0.05
     এতটাই
    0.05
     unclear
    0.05
     અહીં
    0.05
     पूर्
    0.05
     which
    0.05
     regarding
    0.05
     Joint
    0.05
    Activations Density 0.001%

    No Known Activations