© 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. 90486
    Prev
    Next
    INDEX
    Explanations

    watching television programs

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

    The neuron strongly activates on mentions of watching or viewing media (e.g., “watch,” “watching,” “a movie,” sports broadcasts, or news).

    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
    Prod
    -0.83
     прод
    -0.77
    剧本
    -0.76
     Konami
    -0.76
    osta
    -0.76
     listeners
    -0.75
    แห
    -0.73
     IMDG
    -0.73
     prod
    -0.73
     monstru
    -0.73
    POSITIVE LOGITS
     movies
    1.81
     news
    1.41
     documentaries
    1.40
     movie
    1.38
     cartoons
    1.34
     programs
    1.24
     episodes
    1.22
     lectures
    1.20
     videos
    1.17
     documentary
    1.16
    Activations Density 0.048%

    No Known Activations