© 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. 119473
    Prev
    Next
    INDEX
    Explanations

    protein structure data and prediction

    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
    通过
    -0.07
    并通过
    -0.07
     हम
    -0.07
     通过
    -0.06
    通過
    -0.06
    ผ่าน
    -0.06
    র্ষ
    -0.06
     Metal
    -0.06
     tuyển
    -0.06
     melalui
    -0.06
    POSITIVE LOGITS
     data
    0.07
    数据
    0.06
    Data
    0.06
     jigsaw
    0.06
    data
    0.06
    idata
    0.06
     Daten
    0.06
    線の
    0.06
     reconstruction
    0.06
     డే
    0.06
    Activations Density 0.005%

    No Known Activations