© 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. 23831
    Prev
    Next
    INDEX
    Explanations

    Australian government departments and officials

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

    The neuron is tuned to pick out capitalized content words—proper names, acronyms, and heading/title tokens.

    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
     statewide
    -0.87
     échelle
    -0.81
     COMMENTS
    -0.75
     organise
    -0.73
     Kass
    -0.73
     Nederlands
    -0.73
     Cabello
    -0.71
     kar
    -0.70
     kenal
    -0.70
    〝
    -0.70
    POSITIVE LOGITS
     Senators
    1.00
    Australian
    0.97
     DEE
    0.97
     Canberra
    0.96
    Department
    0.94
     Australian
    0.94
    department
    0.92
    Senator
    0.87
     senators
    0.86
    Alban
    0.85
    Activations Density 0.028%

    No Known Activations