© 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. 117465
    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
     terlalu
    -0.07
    ترنت
    -0.07
     troppo
    -0.07
     iria
    -0.07
    可能会
    -0.07
     tersebut
    -0.07
     تلك
    -0.06
     тези
    -0.06
    最初
    -0.06
     которых
    -0.06
    POSITIVE LOGITS
     살아
    0.06
    Extension
    0.06
     both
    0.05
     時計
    0.05
     добиться
    0.05
     Michael
    0.05
     east
    0.05
     ailing
    0.05
     businesses
    0.05
     struggling
    0.05
    Activations Density 0.000%

    No Known Activations