© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117727
    Prev
    Next
    INDEX
    Explanations

    constructor

    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
     технология
    -0.07
     wrappers
    -0.07
     teknologi
    -0.06
    ほか
    -0.06
    時から
    -0.06
     kangaroos
    -0.06
    Capricorn
    -0.06
     balkon
    -0.06
     प्रोज
    -0.06
    กีฬา
    -0.06
    POSITIVE LOGITS
    狰
    0.06
     मल्टी
    0.06
    خصوص
    0.06
     agré
    0.06
     वर्कर्स
    0.05
     quarrel
    0.05
     puesto
    0.05
     strengthening
    0.05
    appe
    0.05
     多
    0.05
    Activations Density 0.005%

    No Known Activations