© 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. 34-GEMMASCOPE-RES-131K
    7. 92095
    Prev
    Next
    INDEX
    Explanations

    Occupational and government job data

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

    The neuron specializes in spotting numeric tokens—digits and numbers as they appear in tables, percentages, years, codes, and similar data.

    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
     sevi
    -0.75
    馋
    -0.75
     APO
    -0.73
     ~/
    -0.73
    éndolo
    -0.73
     dealers
    -0.72
     Обо
    -0.72
     movi
    -0.71
    Clause
    -0.71
    Törté
    -0.70
    POSITIVE LOGITS
     Bureau
    1.42
     BLS
    1.35
     Occupational
    1.31
     projected
    1.19
     outlook
    1.13
     Outlook
    1.11
     Projections
    1.09
     bureau
    1.06
    Bureau
    1.05
    projected
    1.05
    Activations Density 0.018%

    No Known Activations