© 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. 84463
    Prev
    Next
    INDEX
    Explanations

    director of organization

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

    The neuron detects words naming official leadership or administrative titles (e.g. director, president, directorate).

    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
     связанные
    -1.66
     plátano
    -1.54
    nements
    -1.47
    =@"
    -1.46
    culous
    -1.46
    ﭽ
    -1.45
    灃
    -1.45
    ardı
    -1.43
    大量
    -1.42
     cuyos
    -1.42
    POSITIVE LOGITS
     personalización
    1.80
     impresora
    1.74
     inspección
    1.68
     lavadora
    1.64
     inauguración
    1.60
     planificación
    1.60
     réfrig
    1.59
     sostenibilidad
    1.54
     Inſ
    1.52
     carcasa
    1.52
    Activations Density 0.010%

    No Known Activations