© 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. 22-GEMMASCOPE-RES-131K
    4. 12658
    Prev
    Next
    INDEX
    Explanations

    request and related programming terms

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

    The neuron activates on occurrences of the word “request” (and its capitalized form) in code or text, i.e. when referencing request objects or parameters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -1.61
     ‘
    -1.13
    芹
    -1.05
    pertise
    -1.04
     مليون
    -1.02
     šo
    -0.98
    ја
    -0.97
    liert
    -0.96
    licans
    -0.96
    riculture
    -0.96
    POSITIVE LOGITS
    鱘
    1.20
    Сергей
    1.18
     TOKYO
    1.16
    Михаил
    1.14
    ynek
    1.14
     dortmund
    1.09
    offrir
    1.09
     根
    1.09
    😑
    1.09
    んだから
    1.06
    Activations Density 0.018%

    No Known Activations