© 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. 128157
    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
     από
    -0.07
    scientists
    -0.06
     from
    -0.06
    ക്കായി
    -0.06
    hattan
    -0.06
     της
    -0.06
     monoton
    -0.06
    itech
    -0.06
    etan
    -0.05
    dauer
    -0.05
    POSITIVE LOGITS
     http
    0.07
    http
    0.06
     अनुप्रयोग
    0.06
     পূর্ব
    0.06
     https
    0.06
    不想
    0.06
     विशेषता
    0.06
     さ
    0.06
    ULTURAL
    0.05
    ու
    0.05
    Activations Density 0.001%

    No Known Activations