© 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. 38487
    Prev
    Next
    INDEX
    Explanations

    Victorian government and legal matters

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

    The neuron specializes in spotting numeric tokens—years, statistics, counts, and other numbers—in the text.

    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
     Arkansas
    -0.98
    NSW
    -0.93
     Oklahoma
    -0.93
     Brisbane
    -0.91
     rugby
    -0.91
     Illinois
    -0.89
     Queensland
    -0.88
     Hawaii
    -0.86
     NSW
    -0.85
    nsw
    -0.82
    POSITIVE LOGITS
     Melbourne
    1.71
    Melbourne
    1.60
     Geelong
    1.48
    Victorian
    1.29
     Victorian
    1.26
     vm
    1.03
     Vict
    1.03
    Victoria
    1.01
     Victoria
    0.99
    Vict
    0.96
    Activations Density 0.060%

    No Known Activations