© 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. 21736
    Prev
    Next
    INDEX
    Explanations

    dialogue tags

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

    The neuron detects dialogue attribution markers—verbs like “said,” “hissed,” or “growled,” speaker names, and the surrounding quotation punctuation.

    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
     a
    -1.73
     to
    -1.66
     are
    -1.57
     the
    -1.53
     however
    -1.51
     they
    -1.39
     were
    -1.38
     currently
    -1.33
     thus
    -1.33
     However
    -1.30
    POSITIVE LOGITS
    這裡
    1.41
     разные
    1.41
     мы
    1.40
    FUENTES
    1.38
     şeyi
    1.38
    あなたの
    1.35
    Зно
    1.35
     cápsulas
    1.35
    هو
    1.30
     моя
    1.30
    Activations Density 0.008%

    No Known Activations