© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83795
    Prev
    Next
    INDEX
    Explanations

    shipping cost, policy, company

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

    The neuron fires on occurrences of the word “shipping,” especially in headings or labels (e.g. “Shipping & Handling,” “Shipping Cost,” “shipped,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ’
    -3.48
    “
    -2.89
     slated
    -2.52
    女孩子
    -2.44
    老婆
    -2.39
    尤其
    -2.25
    ation
    -2.25
     是
    -2.22
     вышел
    -2.22
    時間
    -2.19
    POSITIVE LOGITS
    鄠
    3.19
    锜
    2.94
    屜
    2.56
    Ꮸ
    2.52
     onze
    2.50
    轫
    2.47
    ve
    2.44
    नलोड
    2.44
    इटम
    2.41
    蚺
    2.39
    Activations Density 0.004%

    No Known Activations