© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76846
    Prev
    Next
    INDEX
    Explanations

    population and census data

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

    The neuron primarily activates on numeric tokens and statistical figures (e.g. census years, population counts, and other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of population statistics for places—especially census-based counts, numeric population figures, and size rankings of cities, counties, or provinces.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    demographic statistics, particularly census population data with numerical values.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     DialogInterface
    -0.80
    lijden
    -0.79
    کنندگان
    -0.78
    priate
    -0.76
     comic
    -0.76
    ractable
    -0.75
    kyr
    -0.73
    粼
    -0.73
     never
    -0.72
    rté
    -0.72
    POSITIVE LOGITS
     population
    4.06
    population
    3.05
     Population
    3.02
    Population
    2.97
     populations
    2.64
    人口
    2.44
     POPULATION
    2.38
     Populations
    2.11
     población
    2.09
     населения
    2.02
    Activations Density 0.077%

    No Known Activations