© 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. 90653
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

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

    This neuron activates on commas in code, markup, or technical data formats.

    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
    after
    -1.87
     貝
    -1.75
     étan
    -1.73
    的一個
    -1.66
    國民
    -1.64
     sintético
    -1.63
     mettez
    -1.62
    because
    -1.60
     greenery
    -1.59
    Hanya
    -1.58
    POSITIVE LOGITS
    </b>
    1.99
     whom
    1.94
    '),
    1.80
     ใน
    1.71
     It
    1.64
    甭
    1.63
     a
    1.63
     fazendo
    1.63
    Hmmm
    1.62
    :])
    1.60
    Activations Density 0.003%

    No Known Activations