© 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. 40544
    Prev
    Next
    INDEX
    Explanations

    tooth followed by dental terms

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

    the word "tooth" in dental and medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the word “tooth” (in headings or running text), effectively detecting mentions of the term.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ᯅ
    -2.86
    ágenes
    -2.63
    喁
    -2.56
     recevrez
    -2.55
    慙
    -2.52
    鯔
    -2.42
    uttgart
    -2.39
     serez
    -2.39
    でしたが
    -2.36
    淝
    -2.33
    POSITIVE LOGITS
    '
    3.44
    </h1>
    2.91
     be
    2.83
    ا
    2.83
     و
    2.81
    a
    2.56
                
    2.52
    也
    2.50
    2
    2.50
     và
    2.50
    Activations Density 0.003%

    No Known Activations