© 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. 10-GEMMASCOPE-RES-131K
    7. 65101
    Prev
    Next
    INDEX
    Explanations

    giggles, giddy, helium

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

    Explanation of neuron 4 behavior: this neuron fires on words that convey high‐energy excitement or giddiness.

    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
     to
    -2.05
    ↵
    -2.00
     Of
    -1.90
     Then
    -1.83
    好的
    -1.77
    '
    -1.72
    ar
    -1.70
     say
    -1.65
    但在
    -1.65
    so
    -1.64
    POSITIVE LOGITS
    0
    2.25
    以上です
    2.23
     parfü
    2.02
    没办法
    1.97
    对方的
    1.87
     techniczne
    1.85
    鑊
    1.80
     parfüm
    1.79
    起码
    1.78
    越来越多
    1.72
    Activations Density 0.009%

    No Known Activations