© 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. 73977
    Prev
    Next
    INDEX
    Explanations

    numbers and rankings

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

    The neuron is keyed to quantitative report language—terms and tokens that introduce or accompany numerical statistics (numbers, percentages, and words like “dropped,” “to,” etc.).

    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
    毎年
    -1.41
    每年
    -1.33
     years
    -1.20
    新浪
    -1.12
    ){$\
    -1.05
    Years
    -1.05
    lında
    -1.05
    如果
    -1.04
    コロナ禍
    -1.02
    Images
    -1.01
    POSITIVE LOGITS
     yesterday
    1.47
     EconPapers
    1.41
     last
    1.40
     week
    1.29
     today
    1.24
    breviations
    1.19
    FFECT
    1.16
     Tuesday
    1.15
     analysts
    1.10
     terbaru
    1.09
    Activations Density 0.023%

    No Known Activations