© 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. 10-GEMMASCOPE-RES-131K
    7. 103071
    Prev
    Next
    INDEX
    Explanations

    youtube links

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

    The neuron detects YouTube video links (e.g. “youtube.com/watch…” URLs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     in
    -2.09
     With
    -2.06
     on
    -1.94
     At
    -1.85
     by
    -1.85
     In
    -1.84
     for
    -1.82
     with
    -1.73
    🎅
    -1.68
     If
    -1.64
    POSITIVE LOGITS
    鱨
    2.19
    VERY
    1.95
    Tetapi
    1.89
    ޏ
    1.86
    </h5>
    1.79
    موقع
    1.77
    Steuer
    1.76
    sprecher
    1.76
    į
    1.76
    ܆
    1.74
    Activations Density 0.016%

    No Known Activations