© 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. 120296
    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
     mientras
    -0.06
    双
    -0.06
    にも
    -0.06
     ਜਾਂ
    -0.06
    providing
    -0.05
    leans
    -0.05
     PROVIDED
    -0.05
    ሮችን
    -0.05
    pointed
    -0.05
     Gonna
    -0.05
    POSITIVE LOGITS
    :
    0.07
     γ
    0.06
    data
    0.06
    idescent
    0.06
     more
    0.06
     −
    0.06
     우리나라
    0.06
     data
    0.06
     কতটা
    0.06
     why
    0.05
    Activations Density 0.000%

    No Known Activations