© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128378
    Prev
    Next
    INDEX
    Explanations

    easy to use

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

    The neuron strongly activates on the word “use” (especially in phrases like “easy to use”), i.e. it detects occurrences of the verb “use.”

    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
     It
    -1.72
     many
    -1.71
     lettore
    -1.66
     more
    -1.66
    が出来
    -1.61
     nemico
    -1.61
    냑
    -1.60
    先是
    -1.57
     vantaggio
    -1.55
     several
    -1.54
    POSITIVE LOGITS
     ترین
    1.80
     of
    1.62
     and
    1.53
    ан
    1.52
     Seigneur
    1.48
    駸
    1.48
    ти
    1.45
     ใช้
    1.44
     sauvages
    1.43
    8
    1.43
    Activations Density 0.014%

    No Known Activations