© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66143
    Prev
    Next
    INDEX
    Explanations

    entity-relationship models

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

    The neuron fires on technical schema-modeling keywords—especially “entity,” “mapping,” and other database/ER-model terms.

    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
     locom
    -0.75
     纳
    -0.75
     reopen
    -0.71
     Marlborough
    -0.69
    幾乎
    -0.69
     ам
    -0.68
    很少
    -0.68
    Награды
    -0.68
     HST
    -0.67
    Closing
    -0.67
    POSITIVE LOGITS
     entity
    1.30
    ENTITY
    1.23
    Entity
    1.23
     Entity
    1.17
    entity
    1.10
     entities
    1.06
     participation
    1.00
    participation
    0.98
    Entities
    0.94
     Participation
    0.91
    Activations Density 0.034%

    No Known Activations