© 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. 6907
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and prices

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

    The neuron fires on numeric expressions—digits, monetary amounts, percentages, dates, and other number-related tokens.

    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
    thed
    -0.91
    ęg
    -0.81
    panou
    -0.78
     номера
    -0.77
     Goul
    -0.77
    ヴェル
    -0.76
     financiamiento
    -0.75
     financiación
    -0.74
    導演
    -0.73
     сталь
    -0.73
    POSITIVE LOGITS
     nominal
    1.19
     token
    1.14
    token
    1.05
     adequacy
    0.95
     юриди
    0.89
    nominal
    0.87
     symbolic
    0.87
     dollar
    0.85
     Dollar
    0.84
     simb
    0.84
    Activations Density 0.013%

    No Known Activations