© 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. 87145
    Prev
    Next
    INDEX
    Explanations

    shot and shot list

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

    The main thing this neuron does is detect references to film-making shot terminology (e.g. “shot,” “close-up,” “camera angles,” “cinematography”).

    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
     управление
    -0.78
    Poems
    -0.75
    Ứng
    -0.74
     videos
    -0.73
     hin
    -0.70
    圖片
    -0.70
    图片
    -0.69
     Mahi
    -0.69
    写真を撮
    -0.68
    Illustration
    -0.68
    POSITIVE LOGITS
     shot
    1.77
     framing
    1.70
     frame
    1.65
     Frame
    1.52
    Shot
    1.51
     shots
    1.50
     framed
    1.48
    shot
    1.44
     frames
    1.42
     Shot
    1.36
    Activations Density 0.011%

    No Known Activations