© 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. 15825
    Prev
    Next
    INDEX
    Explanations

    conditional statements or reasoning

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

    The main thing this neuron does is detect mentions of the words “condition” or “conditions.”

    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
    祸
    0.66
     situation
    0.64
     disconcert
    0.63
     scene
    0.62
    }\,\
    0.61
    igious
    0.61
     tumultuous
    0.60
     Administrative
    0.60
    クシー
    0.60
     Expansion
    0.59
    POSITIVE LOGITS
    ="'$(
    1.04
     condi
    1.02
     条件
    0.98
     조건
    0.94
    条件
    0.93
    조건
    0.93
    COND
    0.93
    條件
    0.90
    kond
    0.87
     Kond
    0.86
    Activations Density 0.158%

    No Known Activations