© 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. 120297
    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
    可能
    -0.07
    有可能
    -0.07
    ō
    -0.07
    可能会
    -0.06
     可能
    -0.06
     namelijk
    -0.06
    包含
    -0.06
    💠
    -0.06
    inclusion
    -0.06
    一个
    -0.06
    POSITIVE LOGITS
     기존
    0.07
    従来の
    0.07
     old
    0.07
     Wednesday
    0.07
     conventional
    0.06
     list
    0.06
     Monday
    0.06
     Thursday
    0.06
     ใน
    0.06
     tried
    0.06
    Activations Density 0.000%

    No Known Activations