© 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. 102675
    Prev
    Next
    INDEX
    Explanations

    employment and job related initiatives

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

    The neuron activates on mentions of government policy initiatives or public program schemes.

    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
    ᑎ
    -0.82
    えました
    -0.77
     STORIES
    -0.77
    compose
    -0.76
    modificar
    -0.76
     präsentiert
    -0.75
    BRANCH
    -0.75
     DST
    -0.75
    micas
    -0.72
    chnung
    -0.72
    POSITIVE LOGITS
     employment
    1.45
     work
    1.45
     jobs
    1.41
     job
    1.27
    employment
    1.12
    jobs
    1.10
     projects
    1.07
     Beschäf
    1.07
     unskilled
    1.01
     labor
    1.00
    Activations Density 0.005%

    No Known Activations