© 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. 129189
    Prev
    Next
    INDEX
    Explanations

    homocysteine

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

    The neuron detects chemical compounds and medical terminology related to homocysteine.

    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
     uſed
    -1.67
    žová
    -1.44
    髏
    -1.43
    寤
    -1.43
    龵
    -1.41
    ギュア
    -1.41
    縂
    -1.39
     समीक्षाएं
    -1.37
     takes
    -1.36
    呖
    -1.36
    POSITIVE LOGITS
    ?
    1.72
    o
    1.70
    {
    1.66
    6
    1.45
    3
    1.39
     \
    1.38
    </b>
    1.38
    怎麼
    1.36
     специалистов
    1.35
     своим
    1.34
    Activations Density 0.078%

    No Known Activations