© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103084
    Prev
    Next
    INDEX
    Explanations

    thrombosis

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

    the medical term "thrombosis" and related thrombotic conditions.

    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
    s
    -5.25
    l
    -3.44
    r
    -3.11
    y
    -2.95
    ाउनलोड
    -2.83
    os
    -2.75
    said
    -2.67
    ﮦ
    -2.64
     untuk
    -2.64
    she
    -2.59
    POSITIVE LOGITS
    摇了
    2.92
    我一
    2.52
     \
    2.50
     beberapa
    2.48
     verschillen
    2.47
     of
    2.39
     somewhat
    2.39
    dreamstime
    2.33
     outras
    2.30
    两年
    2.30
    Activations Density 0.033%

    No Known Activations