© 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. 128776
    Prev
    Next
    INDEX
    Explanations

    year

    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
     प्रेरित
    -0.07
    ෙක්
    -0.07
     tahun
    -0.07
     yearly
    -0.06
     بهتر
    -0.06
     year
    -0.06
     years
    -0.06
    ในปี
    -0.06
     podpis
    -0.06
     année
    -0.06
    POSITIVE LOGITS
    🍲
    0.07
     menudo
    0.06
    美食
    0.06
    料理
    0.06
     route
    0.06
    🍽
    0.06
    route
    0.06
     ধারে
    0.06
     quando
    0.05
     fB
    0.05
    Activations Density 0.001%

    No Known Activations