© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29944
    Prev
    Next
    INDEX
    Explanations

    filming, production, actors, director

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

    The neuron strongly responds to vocabulary tied to film/video production contexts—terms like set, production, producer, filming, photographer, etc.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ľov
    -0.81
    獵
    -0.77
    arkiv
    -0.75
    է
    -0.75
    ciences
    -0.75
     thinkers
    -0.75
     backpacking
    -0.75
    uitton
    -0.74
    atherapy
    -0.73
    Events
    -0.72
    POSITIVE LOGITS
     crew
    2.11
    現場
    1.80
     onset
    1.76
     actors
    1.65
    onset
    1.60
    crew
    1.59
     filming
    1.54
     production
    1.48
     director
    1.46
     actor
    1.44
    Activations Density 0.024%

    No Known Activations