© 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. 117907
    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
     Paul
    -0.06
     perman
    -0.06
     concept
    -0.06
     konsep
    -0.06
     जब
    -0.06
     infinitely
    -0.06
     podpis
    -0.06
     জম
    -0.06
    처럼
    -0.06
    永遠
    -0.05
    POSITIVE LOGITS
    สอง
    0.07
     endothelial
    0.06
     because
    0.06
     Retrieve
    0.06
     Beitrag
    0.06
     deux
    0.06
     meinem
    0.06
     весьма
    0.06
    urada
    0.06
    Occasionally
    0.06
    Activations Density 0.000%

    No Known Activations