© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64396
    Prev
    Next
    INDEX
    Explanations

    film production roles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Vok
    -0.80
    eakers
    -0.77
     envo
    -0.76
     театр
    -0.74
    феры
    -0.74
     装置
    -0.74
     filmmaking
    -0.73
    VIDEOS
    -0.73
    ॑
    -0.72
    nikova
    -0.71
    POSITIVE LOGITS
     assistant
    1.74
     script
    1.54
     sound
    1.44
     lighting
    1.41
     Assistant
    1.40
     crew
    1.31
     Script
    1.23
    Assistant
    1.23
     grip
    1.21
    assistant
    1.20
    Activations Density 0.038%

    No Known Activations