© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130973
    Prev
    Next
    INDEX
    Explanations

    research papers and articles featured

    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
    再び
    -0.07
     adolescent
    -0.07
    自転車
    -0.06
     techno
    -0.06
    还要
    -0.06
     bash
    -0.06
    理工
    -0.06
     biotechn
    -0.06
    放在
    -0.06
     bytes
    -0.06
    POSITIVE LOGITS
    解决了
    0.06
     rendelkez
    0.06
     సంద
    0.06
    lardan
    0.06
     సంవ
    0.05
     বুঝিয়ে
    0.05
     특징
    0.05
    Kr
    0.05
    の特徴
    0.05
    ind
    0.05
    Activations Density 0.007%

    No Known Activations