© 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. 121007
    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
     Conversation
    -0.07
    acquisition
    -0.06
    ieval
    -0.06
     acquisition
    -0.06
     conversation
    -0.06
    ゼン
    -0.06
    ใน
    -0.06
     booth
    -0.06
     그렇게
    -0.06
    ೆಯ
    -0.05
    POSITIVE LOGITS
     routinely
    0.07
     infrequent
    0.06
     sporad
    0.06
     regularly
    0.06
     cargos
    0.06
     সিরিজ
    0.06
     시리즈
    0.06
     sporadic
    0.06
     guaranteeing
    0.06
     వరు
    0.06
    Activations Density 0.004%

    No Known Activations