© 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. 128397
    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
    包含
    -0.07
     іх
    -0.07
    迭代
    -0.06
     glor
    -0.06
     sistem
    -0.06
    Cpp
    -0.06
    本土
    -0.06
     بودند
    -0.06
     ind
    -0.06
    Sorted
    -0.06
    POSITIVE LOGITS
     gewährle
    0.07
     maximise
    0.07
     ক্ষীণ
    0.06
    compliant
    0.06
     sikre
    0.06
    точной
    0.06
    캬
    0.06
     elections
    0.06
     gewährleisten
    0.06
     tenuous
    0.06
    Activations Density 0.000%

    No Known Activations