© 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. 129134
    Prev
    Next
    INDEX
    Explanations

    people, users, roles

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

    The neuron activates on nouns denoting people in specific roles (e.g., individual, customer, employee, passenger, learner, student).

    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
     it
    -1.76
     sorprender
    -1.53
     politika
    -1.50
     invitar
    -1.49
     -
    -1.48
    ”、“
    -1.44
     maestra
    -1.42
     menik
    -1.41
     Recently
    -1.38
    龊
    -1.38
    POSITIVE LOGITS
     who
    2.39
     extraordinaire
    1.61
    因為
    1.61
     cuyos
    1.52
     tabPage
    1.50
     numberWith
    1.50
    ℟
    1.49
     thuy
    1.48
     któ
    1.47
     vong
    1.47
    Activations Density 0.263%

    No Known Activations