© 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. 117952
    Prev
    Next
    INDEX
    Explanations

    Department of Mathematics or Physics

    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
     ഞാൻ
    -0.07
     encourages
    -0.06
    我
    -0.06
    当我
    -0.06
    allowing
    -0.06
     encourage
    -0.06
     ഓരോ
    -0.06
    とにかく
    -0.06
    𒁳
    -0.06
    但我
    -0.06
    POSITIVE LOGITS
    其
    0.06
     în
    0.06
    Ä
    0.06
     государственный
    0.05
    epa
    0.05
    ovar
    0.05
    扩展
    0.05
     և
    0.05
    os
    0.05
     लिखी
    0.05
    Activations Density 0.003%

    No Known Activations