© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119430
    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
    的最
    -0.06
     isten
    -0.06
     befindet
    -0.06
     இங்கே
    -0.06
     পুনরায়
    -0.06
    ۱۳
    -0.06
     என்னுடைய
    -0.05
     包括
    -0.05
     самых
    -0.05
     après
    -0.05
    POSITIVE LOGITS
     allgemeinen
    0.07
     એક
    0.07
     kèm
    0.07
     conocida
    0.06
     próximos
    0.06
     এক
    0.06
     conocido
    0.06
     несколько
    0.06
     because
    0.06
     gelecek
    0.06
    Activations Density 0.000%

    No Known Activations