© 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. 119081
    Prev
    Next
    INDEX
    Explanations

    prognosis and clinical decision

    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
    5
    -0.07
     crowded
    -0.06
    1
    -0.06
    ５
    -0.06
    8
    -0.06
    ８
    -0.06
    2
    -0.06
    0
    -0.06
    7
    -0.06
    ２
    -0.06
    POSITIVE LOGITS
     Questi
    0.07
     hazırlan
    0.07
     verwendet
    0.06
     использовании
    0.06
     bunları
    0.06
    これらの
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    makeConstraints
    0.06
     해결
    0.06
     kvinn
    0.06
    Activations Density 0.018%

    No Known Activations