© 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. 60750
    Prev
    Next
    INDEX
    Explanations

    license information or questions

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

    The neuron strongly activates on wording around “next episode air date”–i.e. phrases asking when or where a TV show’s upcoming episode will air.

    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
     으로
    -0.87
     подсвет
    -0.85
     often
    -0.85
     helped
    -0.85
     oftentimes
    -0.84
    nejšie
    -0.79
     thinks
    -0.78
    
    -0.76
     my
    -0.73
    TotalPrice
    -0.72
    POSITIVE LOGITS
    expected
    1.04
     ждать
    0.99
    黍
    0.94
    glicher
    0.93
     season
    0.91
     Season
    0.88
    canceled
    0.86
    hibitor
    0.86
     vinaigre
    0.86
    izoen
    0.86
    Activations Density 0.005%

    No Known Activations