© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7483
    Prev
    Next
    INDEX
    Explanations

    systematic persecution and murder

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

    The main thing this neuron does is detect numeric tokens and numerical measurements (e.g. floating-point numbers) in the text.

    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
    দ্দা
    0.70
    FileURL
    0.61
    扆
    0.60
     Dorey
    0.59
     Expo
    0.55
     আদায়
    0.55
     dignified
    0.54
     negotiators
    0.54
     関係
    0.54
     जीके
    0.54
    POSITIVE LOGITS
     plague
    1.28
     Plague
    1.25
     plagues
    1.20
     epidemics
    1.19
     extermin
    1.12
     epidemic
    1.11
    瘟
    1.10
     famine
    1.06
     pest
    1.05
     outbreaks
    0.98
    Activations Density 0.196%

    No Known Activations