© 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. 119518
    Prev
    Next
    INDEX
    Explanations

    HD media formats

    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
     tất
    -0.07
     તમામ
    -0.07
     newest
    -0.06
     ყველა
    -0.06
     полностью
    -0.06
     Blocks
    -0.06
     www
    -0.06
    所有的
    -0.06
    🏚
    -0.06
    すべての
    -0.06
    POSITIVE LOGITS
     insbesondere
    0.06
     আজকে
    0.06
     irregularly
    0.06
     christmas
    0.06
     constituted
    0.06
    🥳
    0.06
    整体
    0.06
    🤩
    0.06
                                 
    0.06
    😋
    0.05
    Activations Density 0.003%

    No Known Activations