© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1584
    Prev
    Next
    INDEX
    Explanations

    wait / waiting

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

    The neuron strongly activates on the word “wait” (and its inflected forms like “waiting,” “waited”), detecting mentions of waiting.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    z
    1.16
    zze
    1.13
    رير
    1.10
    reciate
    1.09
    ли
    1.04
    es
    1.02
    a
    1.01
    adikan
    0.98
    ल
    0.97
    ulence
    0.95
    POSITIVE LOGITS
     đợi
    1.37
     awaiting
    1.13
     Wait
    1.09
     기다
    1.02
    Wait
    0.97
    梆
    0.95
    ท์
    0.93
     chờ
    0.93
    ق
    0.93
    waitUntil
    0.92
    Activations Density 0.014%

    No Known Activations