© 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. 118589
    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
    通常
    -0.06
     fewer
    -0.06
     tandis
    -0.06
     compter
    -0.06
     através
    -0.06
    tenant
    -0.05
     two
    -0.05
    不如
    -0.05
     heavier
    -0.05
     সুবিধা
    -0.05
    POSITIVE LOGITS
     Arrival
    0.07
     этого
    0.07
    sigmoid
    0.06
     этом
    0.06
    Arrival
    0.06
    ಈ
    0.06
    Detailed
    0.06
    arrival
    0.06
     tejto
    0.06
     pitching
    0.06
    Activations Density 0.000%

    No Known Activations