© 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. 14341
    Prev
    Next
    INDEX
    Explanations

    minus followed by numbers or symbols

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

    The neuron fires on the subtraction operator (“–” or hyphen) in mathematical expressions.

    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
     oats
    0.68
    剩下
    0.66
     იაპ
    0.64
     हमें
    0.62
    到
    0.61
     равна
    0.60
     반복
    0.59
     mismatched
    0.59
     rinsed
    0.57
     negated
    0.57
    POSITIVE LOGITS
    DateTimePicker
    0.74
    :'',
    0.71
     Veranst
    0.68
    Heute
    0.65
     അദ്ദേഹം
    0.64
    École
    0.64
     homepage
    0.62
    हिणी
    0.62
     Veranstaltungen
    0.62
    international
    0.61
    Activations Density 0.000%

    No Known Activations