© 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. 22-GEMMASCOPE-RES-131K
    7. 13537
    Prev
    Next
    INDEX
    Explanations

    population counts and geographical locations

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

    The neuron detects numerical and statistical details—especially population figures, census years, and other numeric data in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Alquiler
    -1.33
     betaal
    -1.20
    就开始
    -1.16
     estreno
    -1.16
    SALUD
    -1.14
     anadolu
    -1.13
    Приятного
    -1.13
     tavsiye
    -1.13
     poliester
    -1.12
     aplikacji
    -1.12
    POSITIVE LOGITS
    vimento
    1.29
     vinaigre
    1.28
     oreille
    1.26
    <0xA3>
    1.20
     قدیمی
    1.17
    putBoolean
    1.13
    вах
    1.13
    Earlier
    1.12
     feinen
    1.12
    看到
    1.11
    Activations Density 0.062%

    No Known Activations