© 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. 20224
    Prev
    Next
    INDEX
    Explanations

    margin

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

    The neuron activates on the term “margin” (and its plural), especially when it refers to numeric or measured margins in financial, layout, or similar contexts.

    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
    ⧼
    -2.05
     eſſ
    -2.05
    ㆆ
    -2.03
    ⸰
    -1.98
    酲
    -1.94
     広場
    -1.88
     PUSTAKA
    -1.87
     capace
    -1.86
    饂
    -1.83
    鲧
    -1.81
    POSITIVE LOGITS
     "
    2.23
    ra
    1.95
     &
    1.84
     *
    1.78
    ="
    1.77
    —
    1.73
     \
    1.72
     ">
    1.71
    ).
    1.67
     margins
    1.66
    Activations Density 0.003%

    No Known Activations