© 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. 127230
    Prev
    Next
    INDEX
    Explanations

    superlatives following 'the'

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

    The neuron detects extreme qualifiers—words and phrases that express superlatives or uniqueness (e.g. “the most,” “the best,” “only”).

    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
     generasi
    -1.74
     itſelf
    -1.70
     dific
    -1.66
     confortable
    -1.66
    hawatir
    -1.63
    旰
    -1.62
    🖕
    -1.62
     setiap
    -1.60
    🤢
    -1.60
    ХОД
    -1.59
    POSITIVE LOGITS
     reason
    1.68
     этом
    1.52
    叕
    1.50
     starken
    1.47
    就是
    1.46
     aislado
    1.45
      
    1.43
     contain
    1.42
    これに
    1.41
    锤
    1.41
    Activations Density 0.011%

    No Known Activations