© 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. 128009
    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
     presentamos
    -0.06
     dla
    -0.05
     पूर्ण
    -0.05
     vlas
    -0.05
     для
    -0.05
    香港
    -0.05
     vive
    -0.05
     für
    -0.05
     Of
    -0.05
     барои
    -0.05
    POSITIVE LOGITS
     kompakt
    0.07
     அல்லது
    0.07
    τι
    0.06
     anesthetic
    0.06
     Мар
    0.06
     atau
    0.06
    سٹر
    0.06
     কিংবা
    0.06
     madde
    0.06
    ෲ
    0.06
    Activations Density 0.000%

    No Known Activations