© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63908
    Prev
    Next
    INDEX
    Explanations

    employment opportunity affirmative action regulations

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

    The neuron fires on formal equal‐employment‐opportunity and affirmative‐action policy language (e.g. “Equal Opportunity Employer,” nondiscrimination provisions, 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_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
    acjach
    -0.79
    ayos
    -0.79
    ñera
    -0.71
     תש
    -0.71
    密钥
    -0.70
     Accreditation
    -0.69
    AVING
    -0.69
    terno
    -0.68
     Menurut
    -0.68
    Assumption
    -0.68
    POSITIVE LOGITS
     affirmative
    1.06
     Affirmative
    1.04
     hiring
    0.95
    Recruitment
    0.83
     outreach
    0.81
     recruitment
    0.81
    goals
    0.81
    Affirm
    0.80
     job
    0.79
     Stere
    0.79
    Activations Density 0.014%

    No Known Activations