© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 18985
    Prev
    Next
    INDEX
    Explanations

    depreciation and amortization

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

    The neuron fires strongly on financial‐accounting vocabulary, especially terms around amortization, depreciation, assets, and related spreadsheet/calculation words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    partimento
    -2.05
    
    -1.91
    jected
    -1.87
    充满了
    -1.86
    volved
    -1.84
     撮り
    -1.81
    ⎆
    -1.80
    犼
    -1.77
    cepted
    -1.75
    formatics
    -1.75
    POSITIVE LOGITS
    '
    2.31
     $\
    1.73
    ,”
    1.70
     zwanzig
    1.65
    -
    1.64
    ”?
    1.60
     Mittelalter
    1.57
     on
    1.57
    To
    1.55
    ↵
    1.53
    Activations Density 0.002%

    No Known Activations