© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44011
    Prev
    Next
    INDEX
    Explanations

    holy exclamations and phrases

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

    The neuron detects exclamatory interjections expressing surprise or emphasis—especially “holy …” phrases (e.g. “holy cow,” “holy shit”) and similar exclamations like “oh my (god/­lord).”

    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
    -2.41
     has
    -1.99
     said
    -1.86
     is
    -1.77
    によって
    -1.74
     OF
    -1.70
    says
    -1.67
     in
    -1.65
     dando
    -1.60
     
    -1.60
    POSITIVE LOGITS
    呖
    1.91
     calavera
    1.86
     salu
    1.83
    淶
    1.83
    彀
    1.81
    瞜
    1.80
     paloma
    1.79
    ︐
    1.79
    __':
    1.79
    覘
    1.78
    Activations Density 0.003%

    No Known Activations