© 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. 128433
    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
     ভিত্তিতে
    -0.06
    ொரு
    -0.06
     autor
    -0.06
     hvis
    -0.06
     attività
    -0.06
     одина
    -0.06
     hasn
    -0.06
     meiner
    -0.06
     건물
    -0.05
     entanto
    -0.05
    POSITIVE LOGITS
    centerY
    0.06
    ్రహ
    0.06
     появляются
    0.06
    Prom
    0.06
     simplifié
    0.06
    จำ
    0.06
     ലീ
    0.05
    versus
    0.05
     väldigt
    0.05
    真的是
    0.05
    Activations Density 0.000%

    No Known Activations