© 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. 63122
    Prev
    Next
    INDEX
    Explanations

    Wellington and Waterloo historical context

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

    The neuron is detecting mentions of geographic location names (place names).

    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
    siella
    -0.79
    洲
    -0.73
    Sweet
    -0.71
    nocení
    -0.68
    문
    -0.68
     Lynch
    -0.68
    Sports
    -0.67
    弊
    -0.66
    Healing
    -0.66
    α
    -0.65
    POSITIVE LOGITS
     Wellington
    1.72
    Wellington
    1.40
     Waterloo
    1.27
    Waterloo
    1.16
     Wellesley
    1.09
     Napoleon
    0.97
    Napoleon
    0.95
     Aps
    0.83
    chest
    0.81
     Napole
    0.81
    Activations Density 0.015%

    No Known Activations