© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59439
    Prev
    Next
    INDEX
    Explanations

    quantities followed by units

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

    This neuron flags standalone numeric measurements or counts (especially three-digit numbers) in the text.

    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
    懌
    -1.91
    
    -1.88
     internacionais
    -1.84
     протягом
    -1.79
     nacionais
    -1.78
     ห้อง
    -1.76
    
    -1.71
    Setelah
    -1.71
     夜景
    -1.69
    Цита
    -1.68
    POSITIVE LOGITS
     \
    1.93
    屣
    1.85
    ご注意
    1.84
     Перейти
    1.80
     asegura
    1.75
    an
    1.73
     worin
    1.67
    ной
    1.67
          
    1.66
     derselbe
    1.65
    Activations Density 0.021%

    No Known Activations