© 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. 117827
    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
     і
    -0.06
     lawmakers
    -0.06
     the
    -0.06
     vinyl
    -0.06
     much
    -0.06
     और
    -0.06
     scheduling
    -0.06
    vinyl
    -0.06
     saison
    -0.06
    Vinyl
    -0.06
    POSITIVE LOGITS
    再次
    0.08
     opět
    0.07
    আবার
    0.07
     ponownie
    0.07
    再度
    0.07
     Kø
    0.07
    改めて
    0.07
     grâce
    0.06
     graças
    0.06
     வயிற்றில்
    0.06
    Activations Density 0.000%

    No Known Activations