© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91331
    Prev
    Next
    INDEX
    Explanations

    occupations and jobs

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

    The neuron is specialized to detect number tokens (numerical values and digits) in the text.

    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
     opcional
    -0.82
     incendie
    -0.81
    plash
    -0.80
    orium
    -0.80
     página
    -0.79
     bune
    -0.78
    treeview
    -0.77
    •
    -0.77
     narzęd
    -0.77
    loo
    -0.76
    POSITIVE LOGITS
     skilled
    2.30
     unskilled
    1.97
     blue
    1.77
    skilled
    1.75
     managerial
    1.64
     clerical
    1.54
     Skilled
    1.52
     manual
    1.42
    blue
    1.35
     supervisory
    1.30
    Activations Density 0.041%

    No Known Activations