© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1202
    Prev
    Next
    INDEX
    Explanations

    time and questions

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

    The neuron strongly activates on direct instructional or prompting language—e.g., questions and commands from an instructor.

    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
    /
    1.09
     solamente
    0.93
    もしくは
    0.93
     (
    0.93
     emotive
    0.91
    và
    0.89
    (
    0.88
     stets
    0.86
    1
    0.86
    -
    0.84
    POSITIVE LOGITS
     hắn
    1.42
     Qian
    1.16
     Xiang
    1.14
     Xiao
    1.13
     Zhao
    1.11
     Xuan
    1.11
     Xue
    1.09
    
    1.09
     Qin
    1.08
     Qiu
    1.07
    Activations Density 0.031%

    No Known Activations