© 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. 10-GEMMASCOPE-RES-131K
    7. 277
    Prev
    Next
    INDEX
    Explanations

    medical conditions ending in emia

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

    medical condition terms ending in "emia" or "mia" (like anemia, viremia, hyperhomocysteinemia).

    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_10/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
    了
    -2.81
    錞
    -2.61
    上官
    -2.52
    .”
    -2.48
    
    -2.44
    ).
    -2.33
    ではでは
    -2.28
    擄
    -2.27
     и
    -2.23
    ){
    -2.23
    POSITIVE LOGITS
     laterale
    2.13
    sandalia
    2.11
    e
    2.09
    
    2.06
     LastName
    2.06
    ه
    2.05
     russa
    2.03
    Ꝑ
    2.02
    苌
    2.02
     and
    2.00
    Activations Density 0.033%

    No Known Activations