© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14656
    Prev
    Next
    INDEX
    Explanations

    e-commerce or educational terms

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

    The neuron responds to numeric and quantitative tokens—decimal numbers, dates/times, prices, statistics, etc.

    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
    P
    0.90
    T
    0.86
    ia
    0.83
    L
    0.83
    Tl
    0.77
    R
    0.77
    I
    0.75
    ik
    0.74
    Tot
    0.74
    țiile
    0.73
    POSITIVE LOGITS
    elabel
    0.84
     constituyen
    0.84
     بتكون
    0.77
    გორ
    0.76
     اند
    0.75
    しております
    0.75
     становятся
    0.73
     खिलाफ
    0.73
     Umgebung
    0.73
    tails
    0.72
    Activations Density 0.000%

    No Known Activations