© 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. 10-GEMMASCOPE-RES-131K
    4. 65289
    Prev
    Next
    INDEX
    Explanations

    Queensland places and organizations

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

    The neuron activates on mentions of “Queensland” (and its abbreviation QLD).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Когда
    -2.94
     This
    -2.84
     They
    -2.83
     When
    -2.61
     in
    -2.59
     другими
    -2.55
    c
    -2.47
     Of
    -2.44
     เมื่อ
    -2.44
     "
    -2.42
    POSITIVE LOGITS
    驁
    3.48
    橚
    3.23
    婓
    3.11
    殽
    2.98
     rústica
    2.89
    ᯾
    2.75
     mannen
    2.72
     bordada
    2.66
    袛
    2.64
    牁
    2.63
    Activations Density 0.003%

    No Known Activations