© 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. 120081
    Prev
    Next
    INDEX
    Explanations

    supplement use and dosage

    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
    搭配
    -0.07
    কান
    -0.06
     vacanam
    -0.06
    好きな
    -0.06
    毁
    -0.06
    더니
    -0.06
    🎥
    -0.06
     শেষ
    -0.06
    組み合わせ
    -0.06
     mediating
    -0.06
    POSITIVE LOGITS
     artificial
    0.07
    perf
    0.06
     область
    0.06
    補
    0.06
     increase
    0.06
    自体
    0.06
    artificial
    0.06
     aumento
    0.06
    েন্স
    0.06
     rediscover
    0.06
    Activations Density 0.016%

    No Known Activations