© 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. 127915
    Prev
    Next
    INDEX
    Explanations

    dates and names like John Wayne

    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
    organizations
    -0.06
     successfully
    -0.06
     Yangtze
    -0.06
    并没有
    -0.06
     none
    -0.06
     왼쪽
    -0.06
    我們
    -0.06
    
    -0.06
     Generally
    -0.06
     the
    -0.06
    POSITIVE LOGITS
     قبل
    0.07
     sebelum
    0.06
    ก่อน
    0.06
     गिन
    0.06
    ไตล์
    0.06
     charting
    0.05
     موسم
    0.05
     pernah
    0.05
     denen
    0.05
     πριν
    0.05
    Activations Density 0.001%

    No Known Activations