© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9528
    Prev
    Next
    INDEX
    Explanations

    wait or pause

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

    The neuron fires on conversational interruption cues or hesitation markers—e.g. “wait,” “hold up,” “minute,” “…,” “brb”—that signal a speaker pausing or calling attention.

    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
    s
    -1.77
     to
    -1.55
     potranno
    -1.52
     schreef
    -1.40
     a
    -1.34
    led
    -1.34
     potere
    -1.30
     largely
    -1.30
     giocatore
    -1.29
     damal
    -1.28
    POSITIVE LOGITS
     autre
    1.69
    </em>
    1.63
    眈
    1.56
    𝄆
    1.55
     maestros
    1.52
     []:
    1.50
    :{
    
    1.46
    媵
    1.46
     улице
    1.46
    _{
    1.45
    Activations Density 0.003%

    No Known Activations