© 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. 118173
    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
     kecil
    -0.06
    ood
    -0.06
     малень
    -0.06
    정도
    -0.06
     ♪
    -0.06
     రూపాయ
    -0.06
     Vergleich
    -0.06
     identique
    -0.06
    ΠΑ
    -0.06
     vergleich
    -0.06
    POSITIVE LOGITS
     কলকাতার
    0.06
    接觸
    0.06
     souci
    0.06
    问题
    0.06
    anbul
    0.06
     exclu
    0.06
     yaptığı
    0.06
    ptions
    0.06
     conglomer
    0.06
     apoyo
    0.06
    Activations Density 0.000%

    No Known Activations