© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106423
    Prev
    Next
    INDEX
    Explanations

    financial indicators and reporting

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

    The neuron activates on financial or statistical performance markers—numeric values, percentages, and verbs like “jump,” “doubled,” or “plunged”—that signal quantitative changes.

    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
     since
    -0.97
     originalen
    -0.83
     شروع
    -0.82
    Since
    -0.81
    ปี
    -0.80
     until
    -0.78
    Ингредиенты
    -0.78
    bringen
    -0.77
    Oggi
    -0.77
    birthDate
    -0.76
    POSITIVE LOGITS
    GeneratedValue
    0.95
    кульп
    0.85
    ļas
    0.82
    Meter
    0.79
     ₹
    0.77
    subscribe
    0.77
     quarter
    0.76
     يكن
    0.76
    …
    0.76
     Sequential
    0.75
    Activations Density 0.002%

    No Known Activations