© 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. 92263
    Prev
    Next
    INDEX
    Explanations

    Cook County, Illinois

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

    The neuron fires on numeric tokens or parts of numeric expressions—years, distances, addresses, route or zone numbers, and similar numeric identifiers.

    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
    network
    -0.75
    rounder
    -0.73
    condu
    -0.71
     Locator
    -0.69
    chrom
    -0.69
     子
    -0.69
     Abuse
    -0.68
    chige
    -0.68
    亿美元
    -0.68
    γά
    -0.68
    POSITIVE LOGITS
     Southland
    0.90
     hashtags
    0.89
     Crete
    0.81
     interferon
    0.81
    hashtags
    0.76
    ၾ
    0.76
    阈
    0.75
     Homeland
    0.74
    廷
    0.73
     Homestead
    0.73
    Activations Density 0.013%

    No Known Activations