© 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. 129998
    Prev
    Next
    INDEX
    Explanations

    Big Bang Theory

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

    The neuron strongly activates on any token containing the substring “Bang,” whether as a standalone word (e.g. “Bang!”) or within longer words (e.g. “Bangladesh,” “Bangalore,” “Bangash”).

    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
    
    -2.53
    錞
    -2.47
    蕻
    -2.47
    〤
    -2.44
    晙
    -2.42
    玊
    -2.39
    蛧
    -2.36
    胪
    -2.34
    の人に
    -2.33
    摃
    -2.30
    POSITIVE LOGITS
    {
    3.50
    -
    2.63
    [
    2.58
    `
    2.52
    ar
    2.47
    =
    2.38
    (
    2.34
    .
    2.30
     могут
    2.30
     Ironically
    2.28
    Activations Density 0.002%

    No Known Activations