© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63144
    Prev
    Next
    INDEX
    Explanations

    secondary or subordinate

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

    The neuron is keyed to occurrences of the copular/auxiliary verb “be” in its various forms (is, are, was, been, being, would be) and the article “a.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     khả
    -0.87
    Paradox
    -0.85
    楢
    -0.82
    Перед
    -0.79
    雒
    -0.78
     individ
    -0.78
    しくて
    -0.77
     φα
    -0.77
    UpInside
    -0.77
    |}\
    -0.77
    POSITIVE LOGITS
     secondary
    4.69
    secondary
    3.84
    Secondary
    3.52
     Secondary
    3.30
     SECONDARY
    3.00
    SECONDARY
    2.86
     subordinate
    2.52
     secondaire
    2.52
     subsidiary
    2.42
     secundario
    2.39
    Activations Density 0.069%

    No Known Activations