© 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. 30078
    Prev
    Next
    INDEX
    Explanations

    subtitle content and languages

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

    The neuron detects UI or metadata labels related to subtitles (e.g. “Subtitle,” “Sub,” “Tit,” “Les,” “English Subtitles,” 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
    cta
    -0.81
    sche
    -0.80
     themed
    -0.79
    晶
    -0.79
    seli
    -0.79
    向き
    -0.74
    scrollTop
    -0.73
     plaid
    -0.72
    шой
    -0.69
     ча
    -0.69
    POSITIVE LOGITS
     subtitles
    1.53
    titles
    1.30
     Subtitle
    1.19
     subtitle
    1.16
     titles
    1.10
    Subtitle
    1.05
    srt
    1.03
    burned
    1.00
    字幕
    1.00
     eingeb
    0.93
    Activations Density 0.017%

    No Known Activations