© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104895
    Prev
    Next
    INDEX
    Explanations

    hiring 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_10/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
    “
    -2.13
    '
    -1.80
     bygge
    -1.48
    {~
    -1.47
     και
    -1.45
     {
    -1.41
     localizado
    -1.38
     (“
    -1.38
    \
    -1.36
     excel
    -1.35
    POSITIVE LOGITS
     Hire
    1.70
     Instead
    1.66
     to
    1.55
    Jährige
    1.52
     brinquedo
    1.51
     peixe
    1.48
    廛
    1.45
    洐
    1.43
     hiring
    1.42
     принад
    1.41
    Activations Density 0.017%

    No Known Activations