© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8591
    Prev
    Next
    INDEX
    Explanations

    emerging markets and growth economies

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

    The main thing this neuron does is detect numeric values (tokens representing numbers or quantities).

    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
    因为
    -1.88
    菒
    -1.83
     about
    -1.73
     vernac
    -1.69
     唯美
    -1.69
     ſy
    -1.66
    豋
    -1.65
    鉏
    -1.65
    ܆
    -1.62
     emot
    -1.61
    POSITIVE LOGITS
     \
    1.72
     are
    1.62
    当中
    1.43
    咄
    1.37
     शुर
    1.34
     intentar
    1.33
    沕
    1.32
     <>
    1.30
     &
    1.30
    ৄ
    1.30
    Activations Density 0.004%

    No Known Activations