© 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. 19721
    Prev
    Next
    INDEX
    Explanations

    positive experience or opportunity

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

    The neuron detects formulaic “I had the … of” expressions conveying positive experience (e.g. “had the pleasure of,” “had the privilege of,” “good fortune of”).

    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
    dicionado
    -1.47
    鬈
    -1.45
     who
    -1.44
     allgemein
    -1.38
     sollen
    -1.37
     rodzin
    -1.36
    Superview
    -1.33
     bestehenden
    -1.33
    必须
    -1.32
     古着
    -1.32
    POSITIVE LOGITS
    枓
    1.44
    ࿙
    1.39
    Quite
    1.39
    بره
    1.38
    These
    1.36
     of
    1.27
    はこんな感じ
    1.26
    ㄉ
    1.23
    Unfortunately
    1.22
    Bahkan
    1.22
    Activations Density 0.011%

    No Known Activations