© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14382
    Prev
    Next
    INDEX
    Explanations

    order ID, entered, filed, or controller

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

    The neuron consistently flags occurrences of the standalone, capitalized word “Order.”

    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
    which
    -3.30
    咴
    -2.70
    ’
    -2.69
    鷥
    -2.66
    湏
    -2.64
    y
    -2.55
    赑
    -2.53
    䊉
    -2.50
     verlo
    -2.44
    ⌵
    -2.30
    POSITIVE LOGITS
    ly
    2.89
    In
    2.89
    *
    2.53
    ～～
    2.28
     THE
    2.23
     pervasive
    2.22
    ma
    2.19
    麦克
    2.16
    </i>
    2.14
    で
    2.14
    Activations Density 0.006%

    No Known Activations