© 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. 128194
    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
    Not in Any Lists

    No Comments

    Negative Logits
    今まで
    -0.06
     কিরূপে
    -0.06
     •
    -0.06
    また
    -0.06
    いま
    -0.05
     sekä
    -0.05
        
    -0.05
    жность
    -0.05
    ה
    -0.05
    以及
    -0.05
    POSITIVE LOGITS
     कस्टम
    0.06
     चाहें
    0.06
    देशक
    0.06
     funkci
    0.06
    Cep
    0.06
     concedes
    0.06
     with
    0.06
     factores
    0.06
     permitting
    0.06
     fortuit
    0.06
    Activations Density 0.000%

    No Known Activations