© 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. 118201
    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
     which
    -0.08
     которое
    -0.06
    য়া
    -0.06
     as
    -0.06
     którego
    -0.06
     நடந்தது
    -0.05
    ரில்
    -0.05
     उससे
    -0.05
     deadline
    -0.05
    以前
    -0.05
    POSITIVE LOGITS
     comidas
    0.07
     ಖರೀ
    0.06
     нередко
    0.06
     उंच
    0.06
    configured
    0.06
    প্রসঙ্গত
    0.06
     ವಿಧಾನಸ
    0.06
     jaar
    0.06
    卡通
    0.06
     ನನಗೆ
    0.06
    Activations Density 0.000%

    No Known Activations