© 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. 9229
    Prev
    Next
    INDEX
    Explanations

    curate, curator, curation

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

    The neuron detects different forms of words built on the “curat-” root (e.g. curate, curator, curation, curatorial, curated, curating).

    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
    
    -2.03
    戗
    -2.02
    pkins
    -1.93
     imprimée
    -1.91
     Setelah
    -1.86
    禕
    -1.85
     teuer
    -1.85
    gique
    -1.82
    mètres
    -1.80
     Might
    -1.79
    POSITIVE LOGITS
     also
    1.83
    ↵
    1.80
    .’”
    1.78
     comme
    1.77
    ्रीय
    1.76
    ’?
    1.74
    ᠁
    1.70
     still
    1.70
    ية
    1.68
    車は
    1.67
    Activations Density 0.002%

    No Known Activations