© 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. 119901
    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
     six
    -0.07
     шесть
    -0.06
     are
    -0.06
     from
    -0.06
     Where
    -0.06
     так
    -0.06
     там
    -0.06
     пять
    -0.06
     first
    -0.06
     ตั้ง
    -0.05
    POSITIVE LOGITS
     muchos
    0.07
     आणि
    0.07
    link
    0.06
    upload
    0.06
     React
    0.06
     diretta
    0.06
     react
    0.06
     noteworthy
    0.06
     bulldoz
    0.06
     London
    0.06
    Activations Density 0.000%

    No Known Activations