© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49385
    Prev
    Next
    INDEX
    Explanations

    employee, agent, medic, or staff roles

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

    The neuron flags code identifiers (e.g. variable, table, or column names).

    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
     clientes
    -1.12
     landlords
    -0.98
    client
    -0.98
     clients
    -0.97
    patient
    -0.97
     клиентов
    -0.96
    patients
    -0.96
    daughter
    -0.95
     pacientes
    -0.95
     klientów
    -0.94
    POSITIVE LOGITS
     staff
    1.90
     personnel
    1.70
     person
    1.68
     who
    1.45
     employee
    1.38
     responsible
    1.36
    staff
    1.26
     officer
    1.19
     crew
    1.17
    姓名
    1.17
    Activations Density 0.026%

    No Known Activations