© 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. 130137
    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
    获得
    -0.07
     obtenir
    -0.06
    generated
    -0.06
    পুরা
    -0.06
    防止
    -0.06
    を取得
    -0.06
     पूर्वा
    -0.06
     شخص
    -0.06
     algorith
    -0.06
     مجموع
    -0.06
    POSITIVE LOGITS
     three
    0.08
     two
    0.07
     क्योंकि
    0.07
     Although
    0.06
    bet
    0.06
     seperti
    0.06
     five
    0.06
     ponieważ
    0.06
     Because
    0.06
     because
    0.06
    Activations Density 0.000%

    No Known Activations