© 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. 117419
    Prev
    Next
    INDEX
    Explanations

    mercury compounds and environmental concerns

    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
     укреп
    -0.07
     boundary
    -0.06
     unexpectedly
    -0.06
     inesper
    -0.06
     test
    -0.06
    চে
    -0.06
    Bounding
    -0.06
     stunt
    -0.06
     баскет
    -0.06
    तेक
    -0.05
    POSITIVE LOGITS
     thalam
    0.07
    岛
    0.06
    感覺
    0.06
    अलग
    0.06
    iriman
    0.06
     احساس
    0.06
     독립
    0.06
    🐁
    0.06
     negotiating
    0.06
     কিছুর
    0.06
    Activations Density 0.008%

    No Known Activations