© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108727
    Prev
    Next
    INDEX
    Explanations

    job offers and company culture

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

    The neuron fires on promotional or benefit-highlighting words and phrases in job ads—basically the buzzwords that tout perks, pay, emphasis, and positive selling points.

    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
     menghabiskan
    -1.04
     kapasitas
    -0.99
     fortun
    -0.97
    uração
    -0.97
    tifiable
    -0.94
    ⓐ
    -0.92
     kebersihan
    -0.92
    ರ
    -0.92
     Mts
    -0.88
    struzioni
    -0.87
    POSITIVE LOGITS
     flexible
    2.06
     work
    1.56
     culture
    1.48
     flexibility
    1.45
     company
    1.44
     Flexible
    1.43
     pay
    1.41
    flexible
    1.35
    Flexible
    1.35
     salary
    1.30
    Activations Density 0.008%

    No Known Activations