© 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. 115913
    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
     whom
    -0.06
    汲
    -0.06
    将其
    -0.05
     일이
    -0.05
     discussão
    -0.05
     Man
    -0.05
     fordi
    -0.05
     whether
    -0.05
     режима
    -0.05
     Kennt
    -0.05
    POSITIVE LOGITS
     quality
    0.06
     empowers
    0.06
    constraints
    0.06
     empowering
    0.06
    qualität
    0.06
    ผสม
    0.06
    quality
    0.06
     corriente
    0.06
    এই
    0.05
     motorsport
    0.05
    Activations Density 0.000%

    No Known Activations