© 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. 19882
    Prev
    Next
    INDEX
    Explanations

    Grenada, chlorophenyl, Forrest Gump

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

    The neuron strongly activates on specialized scientific terminology—particularly Latin taxonomic names (e.g. genus Diptera: Psychodidae, Phlebotomus) and chemical compound terms (e.g. “dichlor,” “chloro” derivatives).

    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
    ing
    -4.63
    a
    -4.41
    i
    -3.36
    y
    -3.20
     beberapa
    -3.17
    ة
    -3.17
    だけではなく
    -3.09
    o
    -3.03
    だけでなく
    -3.02
    鈇
    -3.00
    POSITIVE LOGITS
     untapped
    3.02
    愎
    3.00
     unrelenting
    2.92
     unparalleled
    2.84
     exacting
    2.77
    ם
    2.75
    澳大利
    2.75
    richlet
    2.73
    ે
    2.73
     špat
    2.67
    Activations Density 0.768%

    No Known Activations