© 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. 10
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized to detect references to organized instructional or training events (e.g. training, lectures, discussions, Q&As, debriefings).

    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
     embroiled
    0.50
    t
    0.49
     airliner
    0.48
     unjustified
    0.47
     undesired
    0.47
    出来了
    0.46
     untrue
    0.46
    0
    0.46
     penalized
    0.45
    1
    0.45
    POSITIVE LOGITS
    を行い
    0.73
    เพื่อ
    0.68
    เพื่อให้
    0.68
    指導
    0.66
    ເພື່ອ
    0.65
     dotyczące
    0.65
    を行います
    0.64
    sessions
    0.63
     webinars
    0.63
    培训
    0.61
    Activations Density 0.000%

    No Known Activations