© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 7193
    Prev
    Next
    INDEX
    Explanations

    await

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

    The neuron detects promotional or persuasive marketing phrases that promise or offer something desirable (e.g. “waiting for you,” “much more to offer,” “abundance of … awaiting,” “a few clicks away,” “trip of a lifetime,” etc.).

    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_31_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
     رکھنے
    0.61
    ющего
    0.58
     ಕಡಿ
    0.57
    isce
    0.56
    íny
    0.54
    চিতে
    0.54
    φορά
    0.53
    rlige
    0.53
    iane
    0.52
    ალური
    0.52
    POSITIVE LOGITS
     await
    3.44
    await
    3.33
     awaits
    2.84
     awaiting
    2.81
     awaited
    2.47
     waiting
    2.27
    等待
    2.08
     Waiting
    2.03
     기다
    2.00
    Waiting
    1.88
    Activations Density 0.023%

    No Known Activations