© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63185
    Prev
    Next
    INDEX
    Explanations

    international events and dates

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

    This neuron responds strongly to mentions of World War I (e.g. “War” + the Roman numeral “I”) and other date or year markers in historical 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
     komment
    -0.94
    Many
    -0.88
    surate
    -0.81
     onError
    -0.80
     integrated
    -0.80
    Here
    -0.80
    quarie
    -0.78
    主页
    -0.78
     الجمعة
    -0.78
     удо
    -0.77
    POSITIVE LOGITS
     diplomatic
    1.24
     League
    1.20
     naval
    1.13
    Neu
    1.09
     Neutr
    1.05
     Britain
    1.05
     France
    1.05
     diplom
    1.05
     international
    1.04
     Germany
    1.04
    Activations Density 0.021%

    No Known Activations