© 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. 75949
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms with associated properties

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

    technical terms from professional fields like medicine, engineering, and science.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly responds to numeric data—quantities, measurements, or statistical values.

    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
     获取
    -1.03
    View
    -0.94
     altercation
    -0.91
     кв
    -0.91
    ที่
    -0.91
     of
    -0.91
     florales
    -0.91
     vitales
    -0.90
     тис
    -0.90
     是否
    -0.88
    POSITIVE LOGITS
    uitable
    1.02
    %。
    1.01
     coverage
    0.99
     parlamento
    0.96
     alug
    0.94
     diesmal
    0.93
    issenschaft
    0.92
     élève
    0.92
     thọ
    0.91
     Beteiligung
    0.91
    Activations Density 0.289%

    No Known Activations