© 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. 117877
    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
     වන්නේ
    -0.07
     মূলত
    -0.06
     Applies
    -0.06
     Brunner
    -0.06
    values
    -0.06
    式的
    -0.06
     отличается
    -0.06
     Allí
    -0.06
    的是
    -0.05
     بداية
    -0.05
    POSITIVE LOGITS
     certaines
    0.07
     algunas
    0.07
     depressions
    0.07
     bazı
    0.07
     некоторых
    0.07
     некоторые
    0.07
     ciertas
    0.07
     niektórych
    0.07
     certains
    0.07
     Некоторые
    0.07
    Activations Density 0.000%

    No Known Activations