© 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. 34-GEMMASCOPE-RES-131K
    7. 49984
    Prev
    Next
    INDEX
    Explanations

    dialogue turns

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

    This neuron detects bits of direct speech or quoted dialogue (e.g. quotation marks, question words, and question marks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     there
    -1.05
    﨑
    -1.02
    avantage
    -0.96
     seen
    -0.94
     talks
    -0.94
     it
    -0.94
    轎
    -0.92
    皱眉
    -0.91
     décide
    -0.91
    Talking
    -0.90
    POSITIVE LOGITS
     replied
    1.94
     response
    1.92
     reply
    1.90
     whereupon
    1.69
     responded
    1.69
     to
    1.60
    reply
    1.59
    response
    1.58
     Response
    1.52
     responses
    1.41
    Activations Density 0.029%

    No Known Activations