© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11857
    Prev
    Next
    INDEX
    Explanations

    protein domains and mathematical domains

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

    The neuron identifies the word "domain" across scientific 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
    ?"
    -3.25
    TintMode
    -2.69
    gucig
    -2.66
     bluza
    -2.56
    elerik
    -2.56
    整个人
    -2.53
    смотра
    -2.47
    ⎚
    -2.44
    思议
    -2.44
    糌
    -2.42
    POSITIVE LOGITS
     tetapi
    3.73
    m
    3.55
    Y
    3.06
    in
    2.91
     enticing
    2.75
    il
    2.70
    <em>
    2.69
      
    2.59
     But
    2.56
    </sup>
    2.52
    Activations Density 0.012%

    No Known Activations