© 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. 129236
    Prev
    Next
    INDEX
    Explanations

    epithelial tissue defects

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ších
    -0.06
     തൂ
    -0.06
     сухо
    -0.06
    Cuáles
    -0.06
     গণহত্যার
    -0.06
     linkages
    -0.06
     美術
    -0.06
     تصميم
    -0.06
     dry
    -0.06
     Hill
    -0.06
    POSITIVE LOGITS
     watermark
    0.06
    紊
    0.06
    我
    0.06
     endothelium
    0.06
     humorous
    0.06
    Software
    0.06
     lelaki
    0.06
     memer
    0.05
     समस्त
    0.05
     hombre
    0.05
    Activations Density 0.001%

    No Known Activations