© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71029
    Prev
    Next
    INDEX
    Explanations

    business roles and departments

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

    This neuron detects mentions of human resources functions and related roles (e.g. HR, human-resources professionals, managers, departments).

    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
    </h2>
    -1.83
     ”
    -1.45
     use
    -1.44
    </h4>
    -1.41
     ....
    -1.35
    ”?
    -1.30
     as
    -1.30
    ,”
    -1.28
    ...”
    -1.27
    }$\\
    -1.26
    POSITIVE LOGITS
    赑
    1.52
    必要がある
    1.38
    cessed
    1.34
    
    1.33
     Paweł
    1.32
     obicei
    1.31
    ຝ
    1.31
    AdvEx
    1.31
     результаты
    1.30
     chocs
    1.30
    Activations Density 0.087%

    No Known Activations