© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37838
    Prev
    Next
    INDEX
    Explanations

    jobs and employment

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

    The neuron activates on numerical figures and statistics (e.g. counts, percentages, rates).

    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
    Unchecked
    -0.88
    项目
    -0.83
    anciers
    -0.79
    NotExist
    -0.79
    
    -0.78
    ordano
    -0.74
     precio
    -0.73
    |[]
    -0.71
    ruce
    -0.71
     condensation
    -0.71
    POSITIVE LOGITS
     jobs
    2.23
     job
    2.19
     employment
    2.13
    job
    1.66
     Employment
    1.63
    jobs
    1.62
     Jobs
    1.59
     Job
    1.56
    Jobs
    1.54
     hiring
    1.52
    Activations Density 0.021%

    No Known Activations