© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9028
    Prev
    Next
    INDEX
    Explanations

    access to

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

    The neuron is highly sensitive to action‐oriented verbs and verb phrases—especially gerunds and modals that mark obligations or ongoing activities (e.g. “pursuing,” “have to,” “taking on”).

    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
    轪
    0.96
     مهر
    0.86
     организа
    0.83
     λειτουργ
    0.83
     koje
    0.80
     Фе
    0.80
    )][
    0.79
     Хер
    0.79
     ）
    0.79
    もちろん
    0.79
    POSITIVE LOGITS
     pronunciation
    0.77
     ventures
    0.75
     sprawling
    0.74
     underscored
    0.74
     foaming
    0.71
     precisa
    0.70
     বসিয়া
    0.69
    liness
    0.69
     indexing
    0.69
     inspecting
    0.69
    Activations Density 0.000%

    No Known Activations