© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116839
    Prev
    Next
    INDEX
    Explanations

    live stream broadcast

    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
    探し
    -0.77
    配音
    -0.73
     iPod
    -0.72
     deposit
    -0.72
     Process
    -0.71
    isEmail
    -0.69
     业
    -0.68
    fe
    -0.67
    SECTOR
    -0.66
     ri
    -0.66
    POSITIVE LOGITS
     live
    3.11
     livestream
    2.42
     Live
    2.36
    Live
    2.31
     LIVE
    2.20
    live
    2.17
    LIVE
    2.16
    直播
    2.06
     broadcast
    1.91
    ライブ
    1.90
    Activations Density 0.022%

    No Known Activations