© 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. 73130
    Prev
    Next
    INDEX
    Explanations

    margin or margins

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

    The neuron activates on occurrences of the word “margin” (in any casing) typically when used as a layout attribute or parameter.

    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
     剤
    -2.25
     But
    -2.03
    nels
    -1.97
    宬
    -1.95
    鲧
    -1.95
    だろ
    -1.92
    蠵
    -1.92
    ꙮ
    -1.84
     However
    -1.80
     The
    -1.80
    POSITIVE LOGITS
     этих
    2.09
    某个
    2.03
    0
    2.02
    骘
    1.95
    就得
    1.91
     diesen
    1.87
     эту
    1.81
    专用
    1.80
    這種
    1.77
    就是这样
    1.77
    Activations Density 0.003%

    No Known Activations