© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113731
    Prev
    Next
    INDEX
    Explanations

    institutional or institutions

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

    The neuron activates on the word “institutional” (including its variants like “institutionalized”) whenever it appears.

    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
    雱
    -2.83
    螣
    -2.30
    燹
    -2.27
    她的
    -2.25
     gewi
    -2.17
    ʯ
    -2.13
    ౮
    -2.11
    ᥬ
    -2.06
    ⑊
    -2.05
     但
    -2.03
    POSITIVE LOGITS
    ’
    2.53
    </h4>
    2.52
    m
    2.19
    ）
    2.11
    g
    2.03
    l
    1.98
    in
    1.96
    p
    1.95
    {
    1.93
    酝
    1.86
    Activations Density 0.011%

    No Known Activations