© 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. 118274
    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
     следующих
    -0.07
     ebenfalls
    -0.07
     by
    -0.07
     עם
    -0.06
     in
    -0.06
     such
    -0.06
     with
    -0.06
    軼
    -0.06
     while
    -0.06
     seura
    -0.06
    POSITIVE LOGITS
     如果
    0.08
    如果
    0.08
     그렇
    0.07
     teknoloj
    0.06
     সবচে
    0.06
     근데
    0.06
     если
    0.06
     teda
    0.06
     tecnología
    0.06
     technology
    0.06
    Activations Density 0.000%

    No Known Activations