© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6210
    Prev
    Next
    INDEX
    Explanations

    unemployment and employment situations

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

    This neuron activates on terms and phrases related to labor‐market dynamics and employment (e.g. labor, market, efficiency, reforms, employment/unemployment).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     நன்க
    0.67
    ☢
    0.60
     prokary
    0.59
     luciferase
    0.59
    દાન
    0.57
     Omphalodes
    0.57
     Nucleic
    0.56
     Acids
    0.56
    akkhand
    0.56
    慑
    0.56
    POSITIVE LOGITS
     unemployment
    2.83
     Unemployment
    2.61
     unemployed
    2.58
     jobless
    2.52
     बेरोजगार
    2.31
     बेरोजगारी
    2.28
     employment
    2.20
     Employment
    2.11
    就业
    2.09
    employment
    2.08
    Activations Density 0.412%

    No Known Activations