© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5011
    Prev
    Next
    INDEX
    Explanations

    instant/immediately/quickly followed by a descriptive word

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

    This neuron detects words (mostly adverbs or temporal expressions) that convey immediacy or rapid occurrence.

    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
    ](../../
    1.03
     شاید
    0.98
     наконец
    0.97
     слегка
    0.96
     Василий
    0.96
     Национальный
    0.93
     ironically
    0.93
    ようやく
    0.93
    終於
    0.92
     Investigative
    0.91
    POSITIVE LOGITS
    바로
    1.29
    すぐ
    1.10
    ة
    1.10
    ing
    1.08
     hemen
    1.06
    یم
    1.04
     imedi
    1.01
    তই
    1.00
     immedi
    0.98
    aneously
    0.97
    Activations Density 0.609%

    No Known Activations