© 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. 76217
    Prev
    Next
    INDEX
    Explanations

    quantities in thousands or millions

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

    This neuron activates on numeric tokens—especially multi‐digit numbers and figures (e.g. counts, monetary amounts).

    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
     :
    -0.85
    lında
    -0.83
    طن
    -0.83
     numero
    -0.80
    Гц
    -0.79
                           
    -0.78
     data
    -0.78
     números
    -0.77
    numbers
    -0.77
     number
    -0.77
    POSITIVE LOGITS
     thousand
    1.95
     hundred
    1.60
    万円
    1.48
     thousands
    1.48
     Thousand
    1.35
     Thousands
    1.34
     million
    1.31
    Thousand
    1.31
    thousand
    1.31
     тысяч
    1.21
    Activations Density 0.031%

    No Known Activations