© 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. 13467
    Prev
    Next
    INDEX
    Explanations

    people going to hospital

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

    mentions of hospitals in news stories, particularly in the context of people being taken to hospitals for medical treatment.

    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
     forêts
    -1.06
    眼下
    -1.03
     élevé
    -1.03
     móds
    -1.02
     メニュー
    -1.02
     шири
    -1.00
     cérami
    -0.98
     -
    -0.98
     quie
    -0.97
     imóvel
    -0.95
    POSITIVE LOGITS
     where
    1.57
    möglichen
    1.34
    霭
    1.34
    起来的
    1.22
    させていただきました
    1.17
     after
    1.11
     but
    1.09
     yesterday
    1.09
     further
    1.08
     with
    1.07
    Activations Density 0.014%

    No Known Activations