© 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. 105702
    Prev
    Next
    INDEX
    Explanations

    workplace personnel

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

    The neuron specifically activates on occurrences of the word “staff.”

    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
    ŚĆ
    -2.41
    ↵
    -2.27
    ŚCI
    -2.11
    乆
    -2.09
     zowel
    -2.09
     filosofía
    -2.08
    vantaged
    -2.06
     mídia
    -2.06
    퐸
    -2.03
    轳
    -2.03
    POSITIVE LOGITS
    e
    2.66
    ac
    2.47
     to
    2.45
    at
    2.38
    的
    2.28
    o
    2.27
    b
    2.23
    I
    2.19
    .”
    2.17
    迎来
    2.16
    Activations Density 0.010%

    No Known Activations