© 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. 9174
    Prev
    Next
    INDEX
    Explanations

    Sustainable Development Goals

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

    This neuron detects specific brand names and products like "Sustainable Development Goals," "Alka-Seltzer," "thrombin," and "HaxeFlixel."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of the phrase “sustainable development” (and closely related mentions such as SDG or development goals).

    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
     Those
    -1.95
    ጵ
    -1.82
     and
    -1.80
    acterísticas
    -1.80
     Они
    -1.77
     作り方
    -1.76
    獁
    -1.75
     Interestingly
    -1.74
    第一章
    -1.74
    鐮
    -1.73
    POSITIVE LOGITS
     одна
    2.03
     ”
    2.02
    V
    1.99
     ''
    1.93
      
    1.90
     regards
    1.86
     ihren
    1.86
    艄
    1.84
     небольшой
    1.84
    J
    1.82
    Activations Density 0.042%

    No Known Activations