© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23469
    Prev
    Next
    INDEX
    Explanations

    supplementary figures or tables

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

    This neuron detects multi-digit numeric tokens (e.g. reference numbers, data values, years) 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
     antaranya
    -0.83
     bendera
    -0.82
     rito
    -0.82
    浏览器
    -0.81
    ctime
    -0.80
     sekitarnya
    -0.80
    telser
    -0.79
    chalten
    -0.79
     dito
    -0.78
     denselben
    -0.77
    POSITIVE LOGITS
     Figure
    5.84
    Figure
    4.94
     Table
    4.75
     Fig
    4.63
    Table
    4.16
    Fig
    3.83
     figure
    3.81
     Figures
    3.33
     Figs
    3.28
     table
    3.19
    Activations Density 0.202%

    No Known Activations