© 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. 128514
    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
    或者是
    -0.07
     tangle
    -0.06
     pross
    -0.06
    特定的
    -0.06
     by
    -0.06
     occuring
    -0.06
    收
    -0.06
    的
    -0.06
    ស
    -0.06
    svet
    -0.06
    POSITIVE LOGITS
    derick
    0.06
    ្
    0.06
     olika
    0.06
     टेक्स्ट
    0.06
    ಿಸುತ್ತ
    0.06
     familiarize
    0.05
     moduleId
    0.05
     werde
    0.05
    eworthy
    0.05
     ако
    0.05
    Activations Density 0.000%

    No Known Activations