© 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. 117153
    Prev
    Next
    INDEX
    Explanations

    medical emergency

    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
     mensuales
    -0.07
     godina
    -0.07
    atorics
    -0.06
     ऑस्ट्रेलिया
    -0.06
     درخت
    -0.06
    +//
    -0.06
     актив
    -0.06
     проект
    -0.06
    ancer
    -0.06
     cic
    -0.06
    POSITIVE LOGITS
     sudden
    0.07
    緊急
    0.06
     precipit
    0.06
     तत्काल
    0.06
     emergency
    0.06
     emergencies
    0.06
     instantly
    0.06
     instantaneously
    0.06
     immediate
    0.06
    Emergency
    0.06
    Activations Density 0.105%

    No Known Activations