© 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. 10-GEMMASCOPE-RES-131K
    4. 23910
    Prev
    Next
    INDEX
    Explanations

    service or services

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

    The neuron strongly activates on the word “service” (and its inflected forms like “services,” “serviced,” etc.).

    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
     distribuidor
    -1.51
     suplemento
    -1.45
    鴟
    -1.41
     enhances
    -1.40
    所谓的
    -1.38
     âme
    -1.37
     محصولات
    -1.33
     bibit
    -1.33
     joga
    -1.33
     corredor
    -1.31
    POSITIVE LOGITS
     and
    1.65
     هذا
    1.52
     Instead
    1.51
     It
    1.46
    さつ
    1.45
     BUT
    1.45
     And
    1.43
    なりません
    1.42
     Then
    1.41
     Immediately
    1.38
    Activations Density 0.028%

    No Known Activations