© 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. 104555
    Prev
    Next
    INDEX
    Explanations

    job applications and candidates

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

    The neuron is tuned to detect mentions of job-application terminology (e.g. “job,” “application,” “CV,” “candidate,” 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
    使用
    -1.04
    entang
    -1.03
    dição
    -1.01
    Ingrédients
    -0.98
    ładka
    -0.96
    年生
    -0.94
    ׇ
    -0.94
     acca
    -0.91
     controla
    -0.91
     Præ
    -0.91
    POSITIVE LOGITS
     job
    2.05
     employment
    1.59
     employer
    1.57
     employers
    1.55
     applicant
    1.53
     hiring
    1.52
     LinkedIn
    1.51
     applicants
    1.42
     jobs
    1.42
     interview
    1.41
    Activations Density 0.074%

    No Known Activations