© 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. 33755
    Prev
    Next
    INDEX
    Explanations

    Napoleon Bonaparte

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

    The neuron responds most strongly to numeric date tokens—particularly years and dates in historical or biographical contexts.

    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
     Parlement
    -0.81
     Ceinture
    -0.78
     parameterized
    -0.77
    🇶
    -0.76
     Platinum
    -0.75
    baha
    -0.75
     Roumanie
    -0.75
    opar
    -0.74
    generation
    -0.73
    circ
    -0.71
    POSITIVE LOGITS
     Napoleon
    2.02
     Bonaparte
    1.88
    Napoleon
    1.73
     Napoleonic
    1.39
     Cors
    1.33
     Napole
    1.33
    poleon
    1.27
    Cors
    1.16
     Empire
    1.16
    Empire
    1.14
    Activations Density 0.023%

    No Known Activations