© 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. 34-GEMMASCOPE-RES-131K
    7. 30413
    Prev
    Next
    INDEX
    Explanations

    religious orders and figures

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

    The neuron strongly activates on structured “infobox”–style metadata—particularly on date numbers, titles, and key role labels in the sidebar summary of a Wikipedia‐style entry.

    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
    Println
    -0.77
    mariage
    -0.74
     paroisse
    -0.73
    kitty
    -0.73
     provider
    -0.72
    的价格
    -0.72
    UnusedPrivate
    -0.72
    htë
    -0.71
     tevreden
    -0.70
    ödie
    -0.70
    POSITIVE LOGITS
     monks
    2.58
     monastery
    2.30
     monk
    2.08
     monastic
    2.06
     monasteries
    1.87
     монасты
    1.77
     Monks
    1.73
     abbey
    1.68
     Monastery
    1.65
     Benedict
    1.60
    Activations Density 0.062%

    No Known Activations