© 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. 22-GEMMASCOPE-RES-131K
    4. 54527
    Prev
    Next
    INDEX
    Explanations

    business departments and roles

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

    The neuron detects mentions of corporate department or functional unit names (e.g. HR, IT, Finance, Legal, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     numerosas
    -1.24
     ofici
    -1.20
    职工
    -1.11
    Recently
    -1.09
     doba
    -1.08
     υπάρχ
    -1.08
     zahlreiche
    -1.08
     ویتامین
    -1.07
     telefonu
    -1.06
     photography
    -1.05
    POSITIVE LOGITS
     department
    1.16
    铛
    1.09
     cópia
    1.06
     in
    1.03
     sarcas
    1.02
    gupta
    1.02
     position
    1.01
    pois
    0.99
     functions
    0.98
     responsible
    0.98
    Activations Density 0.038%

    No Known Activations