© 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. 7979
    Prev
    Next
    INDEX
    Explanations

    expressing surprise or shock

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

    The neuron activates on words and phrases that express surprise or shock (e.g. “surprised,” “shocked,” “aren’t too surprising,” “I’m surprised”).

    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
    杂
    -0.78
    specular
    -0.74
    λια
    -0.74
    雜
    -0.72
    IBC
    -0.72
    шается
    -0.71
     scammers
    -0.71
    Ϝ
    -0.70
    дор
    -0.69
    snippet
    -0.69
    POSITIVE LOGITS
     surprised
    5.44
     surprise
    5.22
     surprising
    4.31
     surprises
    4.25
    surprise
    4.13
     Surprise
    3.88
    surprised
    3.77
    Surprise
    3.61
    Surprised
    3.28
     shocked
    3.23
    Activations Density 0.065%

    No Known Activations