© 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. 120676
    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
     داشته
    -0.07
    ใหม่
    -0.06
    出来
    -0.06
     souha
    -0.06
     তাহারা
    -0.06
     преобразова
    -0.06
     seja
    -0.06
     haben
    -0.05
     комби
    -0.05
    同时也
    -0.05
    POSITIVE LOGITS
     Minimum
    0.07
     deteriorating
    0.06
     or
    0.06
     commencent
    0.06
     enormes
    0.06
     ailes
    0.06
     astonishing
    0.06
     enorme
    0.06
     immense
    0.06
     predominantly
    0.06
    Activations Density 0.000%

    No Known Activations