© 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. 128702
    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
    យ៉ាង
    -0.06
     состоит
    -0.06
    发布的
    -0.06
     zusätzlichen
    -0.06
     culturale
    -0.06
     unmet
    -0.06
     memerlukan
    -0.06
     yolu
    -0.06
     disagreements
    -0.06
     culturais
    -0.06
    POSITIVE LOGITS
     vaik
    0.06
    lichting
    0.06
     presence
    0.06
    Ծ
    0.06
     ग्राहक
    0.06
     tanto
    0.06
    avk
    0.06
    สั่ง
    0.06
     వచ్చ
    0.06
     nä
    0.05
    Activations Density 0.000%

    No Known Activations