© 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. 109366
    Prev
    Next
    INDEX
    Explanations

    spending, using, and reinvesting money

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

    The neuron fires on numeric and financial‐allocation terms—i.e. quantities, money figures, percentages, and words about funding or reinvestment.

    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
    ньому
    -0.91
     vych
    -0.90
    чери
    -0.83
     COSTS
    -0.82
     megh
    -0.79
    收费
    -0.79
    sierten
    -0.77
    ⊄
    -0.77
    Costs
    -0.76
    🛁
    -0.74
    POSITIVE LOGITS
     spend
    2.69
     spent
    2.63
     reinvest
    2.50
     spending
    2.27
     used
    2.23
     Spend
    2.17
     spends
    2.13
    spend
    2.11
    Spend
    2.11
     use
    2.09
    Activations Density 0.049%

    No Known Activations