© 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. 116499
    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
     similaires
    -0.07
    밋
    -0.06
     things
    -0.06
    Waar
    -0.06
     திரை
    -0.06
     similaire
    -0.06
     ഗുരു
    -0.06
     coisas
    -0.06
    多くの
    -0.06
     независимо
    -0.06
    POSITIVE LOGITS
     YouTube
    0.06
     intervenir
    0.06
     προσωπ
    0.05
     tako
    0.05
     dabei
    0.05
     बोलना
    0.05
     Sustainable
    0.05
     personalmente
    0.05
    royo
    0.05
     burada
    0.05
    Activations Density 0.000%

    No Known Activations