© 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. 120831
    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
     गुल
    -0.06
     unclaimed
    -0.06
    യാണ
    -0.06
     schoon
    -0.06
    另
    -0.06
     Other
    -0.06
    可以选择
    -0.06
    frey
    -0.05
     سایر
    -0.05
     serves
    -0.05
    POSITIVE LOGITS
     minimax
    0.06
     faccia
    0.06
     Fortunately
    0.06
     हिंसा
    0.06
     spots
    0.06
     Importing
    0.06
    Fortunately
    0.06
     כי
    0.06
     ઘણા
    0.06
    encja
    0.06
    Activations Density 0.000%

    No Known Activations