© 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. 120747
    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
     northward
    -0.07
     its
    -0.06
     paddling
    -0.06
     titanic
    -0.06
     लंबी
    -0.06
     westward
    -0.06
     reminds
    -0.06
     Winnipeg
    -0.06
     Beograd
    -0.06
     списке
    -0.06
    POSITIVE LOGITS
    特定
    0.06
     specific
    0.06
     να
    0.06
     değişik
    0.06
    Neither
    0.06
    和
    0.06
    不同
    0.06
     δ
    0.06
    ನೀ
    0.06
    者
    0.06
    Activations Density 0.000%

    No Known Activations