© 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. 45116
    Prev
    Next
    INDEX
    Explanations

    husband and wife

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

    The neuron fires on the coordinating “and” when it links to a following title or role (e.g. “and Mrs.,” “and wife,” “and Queen,” “and City Council”).

    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
     first
    -1.97
    if
    -1.87
    At
    -1.85
    ">
    -1.85
    或
    -1.84
    y
    -1.82
    ↵
    -1.79
    ？】
    -1.78
     took
    -1.77
    。
    -1.77
    POSITIVE LOGITS
    狃
    2.08
     dezelve
    2.00
     uyt
    2.00
     enthou
    1.98
    limiento
    1.98
     chirurg
    1.94
    dames
    1.93
     navide
    1.92
    皷
    1.91
    땃
    1.90
    Activations Density 0.004%

    No Known Activations