© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2956
    Prev
    Next
    INDEX
    Explanations

    The neuron flags mentions of waiting or anticipation (e.g. “waiting,” “wait for,” “waiting in line”).

    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
    retto
    0.63
     швидко
    0.61
    iera
    0.59
    erkt
    0.59
    িন্ন
    0.57
     szybko
    0.57
    vino
    0.57
    禦
    0.56
    amik
    0.55
    isee
    0.55
    POSITIVE LOGITS
     waiting
    3.83
     Waiting
    3.45
     wait
    3.41
    Waiting
    3.41
    等待
    3.36
     기다
    3.36
     awaiting
    3.30
     waited
    3.28
    waiting
    3.28
     waits
    3.28
    Activations Density 0.583%

    No Known Activations