© 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. 129338
    Prev
    Next
    INDEX
    Explanations

    JAK, STAT, hormone, ligand detection

    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
     predictors
    -0.07
     geotechnical
    -0.07
     triplicate
    -0.06
     imagem
    -0.06
     Euclidean
    -0.06
    媚
    -0.06
     रज
    -0.06
     maf
    -0.06
     futebol
    -0.06
     modernen
    -0.06
    POSITIVE LOGITS
    ⬤
    0.06
     ollut
    0.06
    打破
    0.06
     пользоваться
    0.06
     QUICK
    0.06
     assis
    0.06
     IFN
    0.06
     queste
    0.05
     직원
    0.05
     rápid
    0.05
    Activations Density 0.001%

    No Known Activations