© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50107
    Prev
    Next
    INDEX
    Explanations

    Christchurch earthquakes

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

    The neuron detects named locations and geographic place names (e.g. Christchurch, Canterbury, Avon River).

    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
    reached
    -0.76
     crescita
    -0.75
     Webseiten
    -0.74
    魈
    -0.74
     expon
    -0.74
     hung
    -0.74
    álise
    -0.72
    racion
    -0.72
     Oakland
    -0.72
    mixed
    -0.72
    POSITIVE LOGITS
     Christchurch
    1.65
     Canterbury
    1.33
     Lyt
    1.05
     earthquake
    1.00
     earthquakes
    0.97
     Earthquake
    0.96
    Earthquake
    0.96
     Avon
    0.96
    Christ
    0.94
     liquef
    0.93
    Activations Density 0.020%

    No Known Activations