© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103820
    Prev
    Next
    INDEX
    Explanations

    promotion and promotional

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

    The neuron activates on “promotion” and its variants (e.g. promotional, promo).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    -3.23
     we
    -3.13
    as
    -3.03
    /
    -3.02
    P
    -2.92
    with
    -2.81
    s
    -2.72
    of
    -2.67
    or
    -2.66
    (\
    -2.64
    POSITIVE LOGITS
     amarela
    2.78
    珖
    2.64
    椟
    2.58
     wana
    2.58
     vermelha
    2.56
    〼
    2.47
     และ
    2.45
    ↵
    2.44
     Boletín
    2.39
    銩
    2.39
    Activations Density 0.008%

    No Known Activations