© 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. 117216
    Prev
    Next
    INDEX
    Explanations

    jobs and employment

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     respuestas
    -0.84
     enfant
    -0.82
     childrens
    -0.80
     デニム
    -0.80
     REQUIRED
    -0.79
     organising
    -0.78
    verb
    -0.77
     yng
    -0.76
    ANDER
    -0.76
     airing
    -0.75
    POSITIVE LOGITS
     employment
    1.63
     training
    1.63
     job
    1.52
     skills
    1.44
     vocational
    1.34
    employment
    1.33
     workforce
    1.30
     work
    1.25
     transitional
    1.24
     employ
    1.20
    Activations Density 0.033%

    No Known Activations