© 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. 34-GEMMASCOPE-RES-131K
    4. 81475
    Prev
    Next
    INDEX
    Explanations

    industry and technology organizations

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

    The neuron is primarily responding to numeric tokens (years, volume and page numbers, reference numbers) in bibliographic or citation contexts.

    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
    gari
    -0.79
     rač
    -0.76
    ГУ
    -0.75
     экологи
    -0.70
     beantworten
    -0.70
    差异
    -0.69
     görüntüsü
    -0.69
     alkalinity
    -0.68
     ГУ
    -0.67
    電子
    -0.67
    POSITIVE LOGITS
     industry
    1.20
     Industry
    1.03
     techn
    1.01
    industry
    1.00
     technical
    0.98
     Process
    0.98
     technolog
    0.95
     technisch
    0.91
     Technology
    0.89
     technische
    0.89
    Activations Density 0.032%

    No Known Activations