© 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. 42578
    Prev
    Next
    INDEX
    Explanations

    Yet followed by contrasting ideas

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

    The neuron responds strongly to the discourse marker “Yet,” especially when it appears sentence-initially.

    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
    îte
    -1.77
    CURLOPT
    -1.58
    椟
    -1.55
    uuuu
    -1.54
     publié
    -1.48
    ₙ
    -1.48
    ydın
    -1.47
    Ꭳ
    -1.45
     materialen
    -1.45
    ٥
    -1.43
    POSITIVE LOGITS
     normalerweise
    1.60
    1
    1.59
    未必
    1.59
     including
    1.55
     erlauben
    1.55
     glaubte
    1.53
     gewiß
    1.50
     where
    1.48
     while
    1.48
    Väl
    1.43
    Activations Density 0.008%

    No Known Activations