© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43353
    Prev
    Next
    INDEX
    Explanations

    professional careers

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

    The neuron strongly activates on occurrences of the word “career” (and closely related phrases like “working life”), effectively marking section headings or mentions of a person’s career.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     they
    -2.14
    泚
    -2.05
    虓
    -1.94
    镚
    -1.80
    梘
    -1.77
    ൎ
    -1.68
    饪
    -1.67
    ῞
    -1.66
     recognized
    -1.65
    能让
    -1.64
    POSITIVE LOGITS
    h
    2.39
    i
    2.11
    是
    2.05
    of
    1.97
    1.91
    q
    1.77
     Всё
    1.71
    ’
    1.70
    ”？
    1.66
    o
    1.65
    Activations Density 0.025%

    No Known Activations