© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11606
    Prev
    Next
    INDEX
    Explanations

    break out / erupt

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

    The neuron specifically detects occurrences of the phrase “broke out,” i.e. that two-word pattern indicating a sudden outbreak or start.

    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
    {
    -2.69
    憮
    -1.96
    are
    -1.85
    埽
    -1.76
    过年
    -1.71
    场的
    -1.69
    after
    -1.69
     و
    -1.66
        
    -1.65
    that
    -1.65
    POSITIVE LOGITS
     in
    2.33
    untamiento
    1.80
     nimmer
    1.79
    Ragnar
    1.78
    情况下
    1.72
     autoridad
    1.70
     Jeśli
    1.70
    垕
    1.69
     Pokud
    1.68
    ㅿ
    1.67
    Activations Density 0.007%

    No Known Activations