© 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. 118114
    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
    ංශ
    -0.07
     متخصص
    -0.07
     наших
    -0.06
     Wilson
    -0.06
     relating
    -0.06
     enhances
    -0.06
     evoking
    -0.06
     accession
    -0.06
     यामध्ये
    -0.06
     наши
    -0.06
    POSITIVE LOGITS
     an
    0.07
     is
    0.07
    Ironically
    0.06
     inital
    0.06
    作为
    0.06
     Ironically
    0.06
    사실
    0.06
     pequeñas
    0.06
    بارك
    0.06
     steht
    0.06
    Activations Density 0.000%

    No Known Activations