© 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. 34-GEMMASCOPE-RES-131K
    4. 87118
    Prev
    Next
    INDEX
    Explanations

    waiting for completion

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

    The neuron fires on expressions of waiting or pending status, especially the phrase “wait for” (and its variants like “waiting for”).

    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
     käytet
    -0.87
    常に
    -0.87
     sisält
    -0.82
    留在
    -0.79
     аренду
    -0.75
    WAITING
    -0.74
     tebal
    -0.73
     Ernesto
    -0.73
     virtù
    -0.72
    蠍
    -0.72
    POSITIVE LOGITS
     until
    1.35
     completion
    1.32
     finish
    1.08
     Completion
    1.02
    until
    0.97
     completing
    0.93
     готов
    0.92
    while
    0.91
    finish
    0.90
     تا
    0.89
    Activations Density 0.021%

    No Known Activations