© 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. 116424
    Prev
    Next
    INDEX
    Explanations

    http://, www

    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
     oprac
    -0.06
     Instead
    -0.06
     чуть
    -0.06
     الأصل
    -0.06
    💻
    -0.06
     অত্যা
    -0.06
    lots
    -0.06
     insertions
    -0.06
    差异
    -0.06
    eras
    -0.06
    POSITIVE LOGITS
     други
    0.06
    怎样
    0.06
    であることを
    0.06
    때
    0.06
    從
    0.05
     третий
    0.05
     tredje
    0.05
    warf
    0.05
    佰
    0.05
    いで
    0.05
    Activations Density 0.003%

    No Known Activations