© 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. 120409
    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
    正在
    -0.07
     accurately
    -0.07
     ursprüng
    -0.07
     hitherto
    -0.07
     occurred
    -0.07
     predetermined
    -0.06
     established
    -0.06
     inability
    -0.06
     pratica
    -0.06
     изначально
    -0.06
    POSITIVE LOGITS
    ↵
    0.07
     new
    0.06
     furthermore
    0.06
    形势
    0.06
     may
    0.06
     giving
    0.06
     лишь
    0.06
     новых
    0.06
    會有
    0.06
    機の
    0.06
    Activations Density 0.000%

    No Known Activations