© 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. 129655
    Prev
    Next
    INDEX
    Explanations

    enzymes

    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
     सेहत
    -0.07
    他是
    -0.06
    គាត់
    -0.06
     exposed
    -0.06
     ayer
    -0.06
     परिवहन
    -0.06
    𝙚
    -0.06
    傌
    -0.06
     McFadden
    -0.06
     Regulations
    -0.06
    POSITIVE LOGITS
     more
    0.08
     göre
    0.07
    According
    0.07
     ditambah
    0.06
     vidéo
    0.06
     ব্যাপ
    0.06
     hilfreich
    0.06
     startling
    0.06
     bigger
    0.06
     according
    0.06
    Activations Density 0.013%

    No Known Activations