© 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. 10-GEMMASCOPE-RES-131K
    7. 70896
    Prev
    Next
    INDEX
    Explanations

    patients with specific conditions

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

    references to people in plural form, especially "those patients" or "those people".

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

    The neuron activates on numeric values—especially numbers and measurements (counts, percentages, or statistics) 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
     bellissima
    -1.52
    PARATUS
    -1.51
     hans
    -1.46
    quelize
    -1.44
     vilka
    -1.42
    bernador
    -1.39
    سياسي
    -1.37
    裒
    -1.37
     雅
    -1.34
    تمبر
    -1.34
    POSITIVE LOGITS
    _
    1.63
     {
    1.38
    转头
    1.33
     niech
    1.30
     schwarzen
    1.26
     powierzchni
    1.25
     traseira
    1.25
     Füße
    1.23
     dianteira
    1.23
    缓缓
    1.22
    Activations Density 0.028%

    No Known Activations