© 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. 59146
    Prev
    Next
    INDEX
    Explanations

    video downloader converter

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

    The neuron fires strongly on phrases about downloading online video content (e.g., “download video from DailyMotion”), i.e. instructions or queries for video‐download actions.

    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
     eki
    -0.85
    ͘
    -0.80
    (())
    -0.80
     damos
    -0.77
    物の
    -0.74
    George
    -0.73
     шли
    -0.72
    savevideobot
    -0.72
    webtoken
    -0.71
     George
    -0.71
    POSITIVE LOGITS
     download
    1.23
     downloader
    1.22
     mp
    1.14
     downloading
    1.13
     MP
    1.09
    Download
    1.01
     converter
    1.00
     Download
    0.99
    Conver
    0.98
    save
    0.96
    Activations Density 0.020%

    No Known Activations