© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117830
    Prev
    Next
    INDEX
    Explanations

    coronary artery bypass surgery

    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
    世界
    -0.06
    武
    -0.06
     पोस्टमार्टम
    -0.06
    水の
    -0.06
    可
    -0.05
     JS
    -0.05
     downtown
    -0.05
    水
    -0.05
     GUID
    -0.05
     water
    -0.05
    POSITIVE LOGITS
    بك
    0.08
    を使用
    0.08
     numerosas
    0.07
     diversas
    0.07
    LOLL
    0.06
     solltest
    0.06
     çeşitli
    0.06
    ToAdd
    0.06
    덫
    0.06
     METAL
    0.06
    Activations Density 0.010%

    No Known Activations