© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39508
    Prev
    Next
    INDEX
    Explanations

    hemorrhage or hemorrhagic

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

    medical terms related to bleeding, particularly "hemorrhage" and "haemorrhagic".

    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
    formatics
    -2.11
     는
    -2.00
    il
    -1.98
    􏿿
    -1.97
    憷
    -1.97
     ';
    -1.93
    憮
    -1.93
    al
    -1.91
    ѣмъ
    -1.89
     bleus
    -1.89
    POSITIVE LOGITS
    ↵
    4.22
     tinham
    2.09
     $
    2.08
     "
    1.98
    ﺰ
    1.88
    สอง
    1.88
     $\
    1.87
    ۹
    1.84
    ів
    1.78
     Geben
    1.76
    Activations Density 0.028%

    No Known Activations