© 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. 12567
    Prev
    Next
    INDEX
    Explanations

    wound healing and repair

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

    The neuron identifies the word "wound" in medical and technical contexts.

    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
    )
    -2.55
    Ꮵ
    -2.53
    呦
    -2.52
    璆
    -2.47
     vulgar
    -2.45
    哟
    -2.44
    ୪
    -2.44
    瀲
    -2.42
    쫀
    -2.42
     Это
    -2.42
    POSITIVE LOGITS
     tetapi
    2.50
    所以在
    2.47
    所以我
    2.45
    同时也
    2.42
    们的
    2.41
    am
    2.34
    骉
    2.31
    圌
    2.30
    但是在
    2.23
    ↵↵
    2.19
    Activations Density 0.004%

    No Known Activations