© 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. 117488
    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
     Vào
    -0.07
     erreurs
    -0.06
    ຕາມ
    -0.06
     была
    -0.06
    вающий
    -0.06
     caribbean
    -0.06
     ZOOM
    -0.06
     عندما
    -0.06
     первая
    -0.06
     डॉक्यूमेंट
    -0.06
    POSITIVE LOGITS
    继续
    0.06
     may
    0.06
     continue
    0.06
     复
    0.06
    引き続き
    0.06
    確実に
    0.06
    繼續
    0.06
     always
    0.05
     associated
    0.05
    可以通过
    0.05
    Activations Density 0.000%

    No Known Activations