© 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. 72795
    Prev
    Next
    INDEX
    Explanations

    dramatic arts and painting

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

    The neuron activates on words naming artistic mediums, disciplines, or creative roles (e.g. painter, engraver, graphic artist, dramatic arts, cinema, dance, theatre).

    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
    おわりに
    -1.41
    你会
    -1.30
    btn
    -1.30
    還會
    -1.29
    還能
    -1.27
    彆
    -1.25
     yetu
    -1.24
     wata
    -1.24
     tanong
    -1.24
    ható
    -1.19
    POSITIVE LOGITS
    したが
    1.42
    сль
    1.35
    luan
    1.30
     但
    1.30
    であるが
    1.26
    aians
    1.25
    啤
    1.25
    嗅
    1.25
    ᴾ
    1.24
     However
    1.23
    Activations Density 0.062%

    No Known Activations