© 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. 8707
    Prev
    Next
    INDEX
    Explanations

    gift for someone

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

    The neuron fires strongly on occurrences of the term “gift” (including “Gift” as part of titles or headings).

    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
    okie
    0.63
    弁当
    0.57
    сант
    0.56
    рях
    0.55
    訓
    0.55
    atra
    0.55
     حزب
    0.54
    سكر
    0.54
    sheet
    0.53
    iemann
    0.53
    POSITIVE LOGITS
     gift
    1.79
     Gift
    1.70
    Gift
    1.63
     GIFT
    1.51
     gifts
    1.46
    🎁
    1.46
    gift
    1.43
     Gifts
    1.43
    礼物
    1.36
     regalo
    1.35
    Activations Density 0.138%

    No Known Activations