© 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. 12155
    Prev
    Next
    INDEX
    Explanations

    stage and scene actions

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

    The neuron fires on structural elements of theatrical scripts—things like act/scene headings, stage‐direction labels, and other play‐format markup.

    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
    éraire
    -0.93
    上涨
    -0.91
     estos
    -0.84
    HPP
    -0.84
     Луч
    -0.82
     también
    -0.82
    blick
    -0.81
    何回
    -0.81
     často
    -0.80
     eikä
    -0.80
    POSITIVE LOGITS
     stage
    1.30
     onstage
    1.25
     exit
    1.20
    Exeunt
    1.16
     enter
    1.15
    Enter
    1.12
     enters
    1.10
     exits
    1.10
     scene
    1.09
     audience
    1.09
    Activations Density 0.002%

    No Known Activations