© 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. 38476
    Prev
    Next
    INDEX
    Explanations

    large monetary sums

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

    The neuron is activated by tokens consisting of multi‐digit numbers (long numeric sequences).

    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
    Thousands
    -0.95
     thousands
    -0.89
    thousands
    -0.81
     Thousands
    -0.77
     UCS
    -0.76
     thousand
    -0.75
     ribuan
    -0.73
    Owner
    -0.67
    doras
    -0.67
     المس
    -0.66
    POSITIVE LOGITS
    億
    1.28
    亿
    0.98
     hundred
    0.98
     hundert
    0.97
     hundreds
    0.95
    hundred
    0.95
     millions
    0.94
     billion
    0.93
     cientos
    0.93
     Hundred
    0.89
    Activations Density 0.087%

    No Known Activations