© 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. 34-GEMMASCOPE-RES-131K
    4. 59816
    Prev
    Next
    INDEX
    Explanations

    Great followed by significant events

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

    The neuron strongly activates on the capitalized adjective “Great” when used in event or era names (e.g. “Great Recession,” “Great Plague,” “Great War”).

    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
    πε
    -0.81
     Trường
    -0.81
     operadores
    -0.78
     cuidados
    -0.77
    āt
    -0.77
     cuidado
    -0.74
     殿
    -0.73
     overflows
    -0.73
     existencia
    -0.72
     batalla
    -0.72
    POSITIVE LOGITS
     compression
    0.85
    compression
    0.83
    Compression
    0.76
     Great
    0.73
     freshest
    0.71
     Чар
    0.69
     Compression
    0.66
    Hun
    0.66
     aina
    0.65
     Supremo
    0.64
    Activations Density 0.046%

    No Known Activations