© 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. 7126
    Prev
    Next
    INDEX
    Explanations

    hepatitis or heparin

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

    The neuron detects forms of "Hep" at the beginning of medical or scientific terms, particularly hepatitis-related content.

    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
     of
    -1.98
    ranslated
    -1.88
     atau
    -1.88
    🫃
    -1.84
     tetapi
    -1.83
    seeking
    -1.81
     naszego
    -1.80
     herhangi
    -1.80
    거나
    -1.78
     francus
    -1.77
    POSITIVE LOGITS
     seems
    1.93
    ◔
    1.88
     {
    1.88
     resembles
    1.85
     a
    1.82
     encompassed
    1.70
    ра
    1.70
    強烈
    1.67
    there
    1.65
     美食
    1.63
    Activations Density 0.003%

    No Known Activations