© 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. 115879
    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
     smoot
    -0.07
     the
    -0.06
    耂
    -0.06
    orous
    -0.05
     pious
    -0.05
     Kı
    -0.05
    讀
    -0.05
     ورد
    -0.05
     complicaciones
    -0.05
    thead
    -0.05
    POSITIVE LOGITS
     "\\
    0.06
     ViewModel
    0.06
    カテゴリー
    0.06
     differentiate
    0.06
     similarity
    0.06
     differentiation
    0.06
     gymnasium
    0.06
     muit
    0.06
     addition
    0.06
     enum
    0.06
    Activations Density 0.000%

    No Known Activations