© 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. 115880
    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
    coffee
    -0.07
    Coffee
    -0.06
    五个
    -0.06
    Atl
    -0.06
    angun
    -0.06
    開業
    -0.06
     hilang
    -0.06
     Coffee
    -0.06
     caffè
    -0.06
    ждений
    -0.06
    POSITIVE LOGITS
     monitoring
    0.07
     stench
    0.06
     sikker
    0.06
     Uttar
    0.06
    다른
    0.06
     if
    0.06
     Sudan
    0.06
     putting
    0.06
     పు
    0.05
     ensuring
    0.05
    Activations Density 0.014%

    No Known Activations