© 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. 129986
    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
     usa
    -0.07
    ড়ী
    -0.06
     আপাতত
    -0.06
     любом
    -0.06
     dedos
    -0.06
     Uses
    -0.06
     kuni
    -0.06
     usare
    -0.06
     ureth
    -0.05
     traversing
    -0.05
    POSITIVE LOGITS
     했다
    0.06
     only
    0.06
    -,
    0.06
     कवर
    0.06
     মানুষদের
    0.06
     것은
    0.06
     একই
    0.06
     would
    0.05
     lote
    0.05
     ಇತರ
    0.05
    Activations Density 0.000%

    No Known Activations