© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12435
    Prev
    Next
    INDEX
    Explanations

    shopping and spending

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

    The neuron activates on numeric tokens (e.g. measurements, monetary amounts, and other numbers).

    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
     sals
    0.64
    舀
    0.56
    Candidate
    0.55
    ıştır
    0.55
    皋
    0.53
    工作室
    0.52
    髯
    0.51
     সর
    0.51
     candidat
    0.51
     Sausage
    0.50
    POSITIVE LOGITS
     shopping
    3.03
     Shopping
    2.95
    Shopping
    2.81
    购物
    2.75
    shopping
    2.73
     malls
    2.55
     शॉपिंग
    2.53
    購物
    2.50
    ショッピング
    2.44
     mall
    2.39
    Activations Density 0.446%

    No Known Activations