© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25832
    Prev
    Next
    INDEX
    Explanations

    sustainable development goals

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

    references to the Sustainable Development Goals or Millennium Development Goals.

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

    This neuron lights up on extremely frequent function words (common “stop words”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    皑
    -0.79
    焦点
    -0.77
     skis
    -0.77
    duire
    -0.76
     wrong
    -0.76
     tubes
    -0.75
     faithful
    -0.75
     genutzt
    -0.74
     dientes
    -0.74
    escu
    -0.73
    POSITIVE LOGITS
     Agenda
    1.84
     SDG
    1.61
     Sustainable
    1.59
     SDGs
    1.56
    Agenda
    1.53
    SDG
    1.35
     Goals
    1.27
    agenda
    1.25
     Goal
    1.21
    Sustainable
    1.20
    Activations Density 0.011%

    No Known Activations