© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118222
    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
    気軽
    -0.06
     téléphonique
    -0.06
     murmured
    -0.06
     whispered
    -0.05
     mn
    -0.05
     लंबे
    -0.05
     xi
    -0.05
    stehen
    -0.05
    Ex
    -0.05
     audible
    -0.05
    POSITIVE LOGITS
    ਿਆਂ
    0.07
     самой
    0.06
     इसमें
    0.06
     বাধা
    0.06
     mouvements
    0.06
    Según
    0.06
     도움이
    0.06
    泍
    0.06
     ござい
    0.06
     Massimo
    0.06
    Activations Density 0.000%

    No Known Activations