© 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. 117593
    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
     review
    -0.06
    review
    -0.06
     reviews
    -0.06
     foothold
    -0.06
     oe
    -0.06
    merksamkeit
    -0.06
     individuality
    -0.06
    尽快
    -0.05
     প্রহ
    -0.05
     spite
    -0.05
    POSITIVE LOGITS
     기억
    0.07
     بہ
    0.07
     glav
    0.07
     ആയിരുന്നു
    0.07
     финансовых
    0.06
     Великой
    0.06
     جناب
    0.06
     تاریخی
    0.06
     Derive
    0.06
     storico
    0.06
    Activations Density 0.000%

    No Known Activations