© 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. 3740
    Prev
    Next
    INDEX
    Explanations

    Yes, introducing statements

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

    The neuron strongly detects the discourse marker “Yes,” (the word “Yes” often followed by a comma) at the start of a clause.

    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
     is
    -1.85
    </h2>
    -1.83
     $
    -1.47
    \
    -1.45
     создать
    -1.41
     pères
    -1.40
    しまった
    -1.39
    стый
    -1.36
    的情况
    -1.34
    )
    -1.34
    POSITIVE LOGITS
    1.98
    1.90
    1.84
    1.81
    1.80
    1.78
    But
    1.77
    1.74
    1.73
    1.71
    Activations Density 0.011%

    No Known Activations