© 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. 34-GEMMASCOPE-RES-131K
    7. 81304
    Prev
    Next
    INDEX
    Explanations

    science and scientists

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

    references to scientific and academic content, including journals, publications, and technical terms.

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

    This neuron strongly activates on numeric tokens (and adjoining punctuation like slashes, dots, underscores, and dashes) such as years, digits, or URL path segments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    /[
    -0.77
     fender
    -0.76
     theorists
    -0.75
    陣
    -0.75
    áll
    -0.73
     turntable
    -0.73
     bizi
    -0.71
    忪
    -0.71
    شنامه
    -0.71
    PHO
    -0.69
    POSITIVE LOGITS
     science
    1.66
     Science
    1.58
    Science
    1.49
    science
    1.32
     SCIENCE
    1.16
     ciencia
    1.15
     Sci
    1.12
    科学
    1.07
     Scientists
    0.98
    SCIENCE
    0.98
    Activations Density 0.031%

    No Known Activations