© 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. 117054
    Prev
    Next
    INDEX
    Explanations

    for each in loops

    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
     only
    -0.07
     chỉ
    -0.07
     тільки
    -0.07
    のみ
    -0.07
     kurta
    -0.06
     인수
    -0.06
     только
    -0.06
     csak
    -0.06
    ดิน
    -0.06
     المقسوم
    -0.06
    POSITIVE LOGITS
    每个
    0.07
     каждым
    0.07
    每一个
    0.06
    每個
    0.06
     பற்றிய
    0.06
    images
    0.06
     каждому
    0.06
     сра
    0.06
    Every
    0.06
     заниматься
    0.06
    Activations Density 0.148%

    No Known Activations