© 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. 15837
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric‐quantitative expressions—tokens involved in numbers, rates, percentages, and amounts.

    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
     yada
    0.70
     &/
    0.64
     ಅಥವಾ
    0.59
     audiov
    0.59
     declaratory
    0.59
     dentre
    0.59
     yah
    0.58
     pornography
    0.58
     checkboxes
    0.58
     veya
    0.57
    POSITIVE LOGITS
    逆
    0.86
     Reversed
    0.77
     تغییر
    0.68
    reverse
    0.68
    Reverse
    0.67
    新的
    0.66
    เปลี่ยน
    0.65
    更改
    0.65
     Reverse
    0.64
     تغيير
    0.64
    Activations Density 0.816%

    No Known Activations