© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68203
    Prev
    Next
    INDEX
    Explanations

    emergency department care

    np_acts-logits-general · gemini-2.5-flash-lite

    content about healthcare systems and medical facilities, particularly in contexts of emergencies or crises.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lantaran
    -1.23
    ׇ
    -1.20
     religieux
    -1.14
    lijk
    -1.07
     apapun
    -1.06
    oplasts
    -1.06
     prêtre
    -1.05
     Theologie
    -1.05
    ⌃
    -1.04
     chré
    -1.02
    POSITIVE LOGITS
    ִּ
    1.52
    ּוֹ
    1.43
     popolazione
    1.40
     gastronomía
    1.34
     capacity
    1.34
    ַּ
    1.30
    ベーター
    1.30
     lidé
    1.28
     วาด
    1.27
     Wednesday
    1.25
    Activations Density 0.009%

    No Known Activations