© 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. 119801
    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
    Either
    -0.06
     Either
    -0.06
    either
    -0.05
    려면
    -0.05
     entweder
    -0.05
     Beware
    -0.05
    urized
    -0.05
     발표
    -0.05
    ([[
    -0.05
    সিড
    -0.05
    POSITIVE LOGITS
     );
    0.07
     documented
    0.07
     ).
    0.07
     ит
    0.06
    histo
    0.06
    佇
    0.06
    层的
    0.06
    에서도
    0.06
     perhaps
    0.06
    支援
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.