© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75008
    Prev
    Next
    INDEX
    Explanations

    salutations starting with dear

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

    This neuron detects the salutation “Dear” at the start of letters or messages.

    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
    ↵
    -2.41
    ឵
    -2.25
     Häufig
    -2.14
     "
    -2.13
    など
    -2.08
     одна
    -2.03
     เพราะ
    -1.98
    Упаковка
    -1.98
     Çünkü
    -1.94
     первая
    -1.91
    POSITIVE LOGITS
    ſſel
    2.92
    who
    2.69
    幛
    2.67
    埽
    2.61
    s
    2.52
    you
    2.50
    
    2.45
     westfalen
    2.39
    镡
    2.34
    硨
    2.20
    Activations Density 0.003%

    No Known Activations