© 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. 116984
    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
     Để
    -0.06
     массив
    -0.06
     Seperti
    -0.06
     وكانت
    -0.06
     Và
    -0.06
     deportation
    -0.06
     مفت
    -0.06
    숏
    -0.06
     LAW
    -0.05
     décider
    -0.05
    POSITIVE LOGITS
    、
    0.08
    ্রান্ত
    0.06
     كمان
    0.06
    ichni
    0.06
     அடித்த
    0.06
     Chaplain
    0.06
     describing
    0.06
     flourishing
    0.06
     என்னுடைய
    0.06
    ர்கள்
    0.06
    Activations Density 0.000%

    No Known Activations