© 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. 10-GEMMASCOPE-RES-131K
    7. 114104
    Prev
    Next
    INDEX
    Explanations

    CDC

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

    The neuron strongly activates on occurrences of the acronym “CDC” (Centers for Disease Control and Prevention).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    '
    -3.86
    ↵↵
    -3.33
    }
    -2.81
     But
    -2.75
     accolades
    -2.64
    杁
    -2.59
    "
    -2.50
     Only
    -2.45
    !)
    -2.45
     A
    -2.33
    POSITIVE LOGITS
     内衣
    4.34
    焿
    4.06
    삵
    3.67
    趼
    3.41
     短发
    3.36
    
    3.16
     火鍋
    3.11
     炖
    3.08
     休閒
    3.05
    ㍑
    3.02
    Activations Density 0.003%

    No Known Activations