© 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. 75950
    Prev
    Next
    INDEX
    Explanations

    footballers' history

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

    The neuron specializes in spotting four‐digit numeric tokens that represent years (date references).

    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
    TextMessage
    -0.77
    TextChanged
    -0.76
     crispy
    -0.75
    عار
    -0.74
     anak
    -0.71
    辛
    -0.71
     euros
    -0.69
    BMP
    -0.69
    Spice
    -0.68
     cocaine
    -0.68
    POSITIVE LOGITS
     дово
    0.90
     thirties
    0.88
     Babe
    0.87
     Gabby
    0.85
     Mahatma
    0.84
     WWI
    0.82
     wartime
    0.81
     Yiddish
    0.81
     Hitler
    0.75
    Mae
    0.75
    Activations Density 0.062%

    No Known Activations