© 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. 22-GEMMASCOPE-RES-131K
    7. 67518
    Prev
    Next
    INDEX
    Explanations

    excited and eager

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

    The neuron fires on words and phrases conveying high-energy positive emotion—excitement, enthusiasm, and eagerness.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     elite
    -0.87
     or
    -0.86
     in
    -0.85
     is
    -0.84
     Elite
    -0.84
     предпоч
    -0.83
     only
    -0.83
    نجان
    -0.83
    ída
    -0.79
     khô
    -0.79
    POSITIVE LOGITS
     excited
    2.00
     excitement
    1.99
     excitedly
    1.91
    Excited
    1.77
    excited
    1.76
     Excited
    1.76
     enthusiasm
    1.66
     enthusiastic
    1.62
     excit
    1.61
     excites
    1.42
    Activations Density 0.034%

    No Known Activations