© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8140
    Prev
    Next
    INDEX
    Explanations

    system and system-related contexts

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

    The neuron primarily detects occurrences of the word “System” (and its plural “Systems”) in various contexts.

    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
     Dri
    0.65
     Textured
    0.63
     الاشكال
    0.63
    CHER
    0.63
    ทางการ
    0.61
    وح
    0.59
     Directly
    0.59
    쌀
    0.58
     Direct
    0.57
    愕
    0.57
    POSITIVE LOGITS
    Sys
    1.02
    syst
    1.01
     syst
    1.00
     sys
    0.98
     Sys
    0.98
     System
    0.95
    system
    0.93
    System
    0.91
    sys
    0.91
    Syst
    0.91
    Activations Density 0.127%

    No Known Activations