© 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. 74417
    Prev
    Next
    INDEX
    Explanations

    serve a function or role

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

    This neuron activates on occurrences of the word “serve” (in any context or usage).

    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
     \
    -2.73
    2
    -2.73
    姈
    -2.55
    3
    -2.47
    ي
    -2.42
    5
    -2.38
     of
    -2.38
    鹩
    -2.22
    geſ
    -2.13
     '
    -2.02
    POSITIVE LOGITS
    .
    2.58
     serves
    2.48
    🎦
    2.27
    辔
    2.19
    ’.
    2.19
    杙
    2.13
    ꙳
    2.13
     serve
    2.09
    πουργ
    2.05
    ).
    2.03
    Activations Density 0.009%

    No Known Activations