© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22703
    Prev
    Next
    INDEX
    Explanations

    dialogue markers

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

    The neuron detects script‐style dialogue markers, i.e. speaker names (in all caps) and the opening quotation marks that introduce spoken lines.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     annen
    -1.60
    ⵌ
    -1.43
    
    -1.41
    Вариант
    -1.40
     jugu
    -1.33
     akku
    -1.33
    Mutability
    -1.32
     them
    -1.31
     Feuchtigkeit
    -1.30
     also
    -1.30
    POSITIVE LOGITS
    是怎么回事
    1.57
    すべて
    1.52
    ৢ
    1.45
    웁
    1.44
    全て
    1.37
    应该是
    1.33
    WORTH
    1.30
    ttää
    1.30
    ittää
    1.30
    garder
    1.30
    Activations Density 0.009%

    No Known Activations