© 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. 124036
    Prev
    Next
    INDEX
    Explanations

    dye applications

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

    The neuron detects the word "dye" in scientific 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
    J
    -3.34
    .)
    -3.06
    U
    -3.05
     So
    -2.95
     .
    -2.83
    敉
    -2.83
    ”
    -2.81
    n
    -2.78
     इत
    -2.70
     {
    -2.64
    POSITIVE LOGITS
    瘆
    2.69
    ла
    2.59
    ܆
    2.56
    凇
    2.50
     ciment
    2.50
     اشار
    2.50
    ↭
    2.45
    棡
    2.44
     IBRARY
    2.42
     ofere
    2.41
    Activations Density 0.013%

    No Known Activations