© 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. 92516
    Prev
    Next
    INDEX
    Explanations

    Australian regions

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

    The neuron specializes in spotting Australian geographic 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
     learn
    -0.78
     thả
    -0.75
     contacted
    -0.73
     script
    -0.73
     phishing
    -0.72
    ManyToMany
    -0.72
     Estuary
    -0.71
    Verwendung
    -0.71
    inose
    -0.69
    [@
    -0.68
    POSITIVE LOGITS
     cowboys
    0.90
     CSU
    0.84
    橿
    0.82
     Thunderbolt
    0.80
     berechnet
    0.77
    🚛
    0.76
     outback
    0.76
     Hereford
    0.75
    TOUR
    0.75
    Texas
    0.74
    Activations Density 0.023%

    No Known Activations