© 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. 117970
    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
     الجديد
    -0.06
     নিলে
    -0.06
     cinque
    -0.05
    王国
    -0.05
     пяти
    -0.05
    Пе
    -0.05
     cuatro
    -0.05
    そもそも
    -0.05
     possibility
    -0.05
    gruppe
    -0.05
    POSITIVE LOGITS
     distributors
    0.06
     !
    0.06
     înce
    0.06
     ততক্ষণ
    0.06
    然后在
    0.06
    äche
    0.06
     dawa
    0.06
     あの
    0.06
     그러니까
    0.06
     painstakingly
    0.06
    Activations Density 0.000%

    No Known Activations