© 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. 130494
    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
     incluidas
    -0.06
     понятно
    -0.06
     confronti
    -0.06
     Aufgabe
    -0.06
     realistically
    -0.06
     that
    -0.06
     столь
    -0.06
     consideramos
    -0.06
     বিশেষজ্ঞরা
    -0.06
     including
    -0.06
    POSITIVE LOGITS
     সার্বভৌম
    0.06
    整个
    0.06
    只会
    0.06
    整個
    0.06
     phạm
    0.06
    BackButton
    0.06
     stunts
    0.06
     sexta
    0.06
     landscapes
    0.06
     imó
    0.06
    Activations Density 0.000%

    No Known Activations