© 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. 107537
    Prev
    Next
    INDEX
    Explanations

    earnings and winnings

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

    The main thing this neuron does is detect numeric tokens and numerical expressions.

    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
     Costs
    -0.83
     protection
    -0.82
    Costs
    -0.78
     затра
    -0.77
    logr
    -0.76
     FishBase
    -0.75
     pesada
    -0.74
    protection
    -0.73
     costly
    -0.72
    日から
    -0.72
    POSITIVE LOGITS
     earnings
    1.50
     earned
    1.16
     earners
    1.15
     earning
    1.12
    earnings
    1.10
    Earnings
    1.05
    earned
    0.98
     earn
    0.97
     winnings
    0.96
     incomes
    0.92
    Activations Density 0.008%

    No Known Activations