© 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. 84774
    Prev
    Next
    INDEX
    Explanations

    increase, growth, sales, rates, and numbers

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

    The neuron fires strongly on numeric figures and financial metrics (e.g., profit, revenue, percentages, dates, monetary amounts).

    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
    睫毛
    -0.72
     야
    -0.69
    ensing
    -0.69
     desigual
    -0.69
    öglich
    -0.69
     racional
    -0.68
    psd
    -0.68
     ГУ
    -0.67
    Rankings
    -0.67
    端末
    -0.67
    POSITIVE LOGITS
     values
    0.88
    การณ์
    0.84
    silience
    0.83
    тивный
    0.81
    VALUES
    0.79
     comte
    0.79
     kteří
    0.78
    Development
    0.78
     Rek
    0.77
    [-
    0.77
    Activations Density 0.040%

    No Known Activations