© 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. 89886
    Prev
    Next
    INDEX
    Explanations

    current user location

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

    The neuron activates on mentions of geographic location or positioning (e.g. “current location,” “distance,” “get … location,” coordinates), i.e. it detects references to retrieving or measuring a place.

    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
    ysaccharide
    -0.85
    createCanvas
    -0.84
     熊
    -0.82
    strtotime
    -0.82
    лод
    -0.81
     parete
    -0.79
    dAtA
    -0.79
    ダー
    -0.79
    glement
    -0.77
    数字
    -0.77
    POSITIVE LOGITS
     location
    3.02
     current
    2.14
    location
    1.98
     Location
    1.93
    Location
    1.77
     locations
    1.73
     whereabouts
    1.62
     position
    1.59
     LOCATION
    1.56
    Current
    1.55
    Activations Density 0.045%

    No Known Activations