© 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. 22-GEMMASCOPE-RES-131K
    7. 73202
    Prev
    Next
    INDEX
    Explanations

    working conditions or job descriptions

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

    The neuron fires on spans that describe on-the-job or company work experiences—e.g. it strongly lights up for phrases like “working at Google” or “worst part of working at ….”

    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
     ricette
    -1.12
    ᐈ
    -1.10
     fiore
    -1.04
     cavo
    -1.02
     bringe
    -1.02
    ಇ
    -1.00
     puntata
    -0.99
    Hvem
    -0.98
     ristorante
    -0.97
     knop
    -0.97
    POSITIVE LOGITS
     work
    1.38
     job
    1.22
     employee
    1.17
     werken
    1.16
     jaké
    1.15
     career
    1.14
     working
    1.13
    anthene
    1.13
    ,
    1.09
     çiz
    1.08
    Activations Density 0.002%

    No Known Activations