© 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. 22-GEMMASCOPE-RES-131K
    4. 28353
    Prev
    Next
    INDEX
    Explanations

    contrary, meanwhile, on the other hand

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

    This neuron detects discourse-marker phrases that signal a shift or contrast in the text (e.g. “on the other hand,” “on the contrary,” “by contrast,” “meanwhile,” “of course,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     camiset
    -1.73
     italie
    -1.68
     botines
    -1.65
    なんですよ
    -1.62
    鱨
    -1.59
     récol
    -1.59
     helicópter
    -1.56
     obrázok
    -1.55
    denn
    -1.55
     ujar
    -1.55
    POSITIVE LOGITS
     is
    3.53
     are
    3.06
     will
    2.80
     was
    2.80
     would
    2.38
     has
    2.34
     should
    2.31
     could
    2.16
     can
    2.14
    is
    2.09
    Activations Density 0.037%

    No Known Activations