© 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. 129481
    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
     devenue
    -0.07
    /
    -0.05
     abruptly
    -0.05
     lt
    -0.05
     became
    -0.05
     involving
    -0.05
    became
    -0.05
    /\
    -0.05
     unsuccessfully
    -0.05
     become
    -0.05
    POSITIVE LOGITS
     akár
    0.08
    往往
    0.07
     Comité
    0.07
     a
    0.07
     właśnie
    0.06
     Così
    0.06
    全て
    0.06
     couture
    0.06
     kahit
    0.06
     khắp
    0.06
    Activations Density 0.000%

    No Known Activations