© 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. 120947
    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
     might
    -0.08
     двох
    -0.08
     কিংবা
    -0.07
     могло
    -0.06
     could
    -0.06
    🍘
    -0.06
     gets
    -0.06
     may
    -0.06
    可能
    -0.06
    可能会
    -0.06
    POSITIVE LOGITS
     lyr
    0.06
    ডেল
    0.06
    setAttribute
    0.06
     songwriting
    0.06
    lect
    0.06
    ToRemove
    0.05
     acel
    0.05
    Develop
    0.05
    έρ
    0.05
    ทุก
    0.05
    Activations Density 0.000%

    No Known Activations