© 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. 116060
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    igil
    -0.06
     offers
    -0.06
     কয়েকটি
    -0.06
    citations
    -0.06
    offers
    -0.06
    prüfung
    -0.06
    いくつかの
    -0.06
     Offers
    -0.06
     одному
    -0.06
    িকভাবে
    -0.06
    POSITIVE LOGITS
     mereka
    0.06
     их
    0.06
     નજી
    0.06
     helplessness
    0.06
     беремен
    0.06
     เช
    0.06
     besi
    0.06
    З
    0.05
     iskust
    0.05
    倝
    0.05
    Activations Density 0.000%

    No Known Activations