© 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. 34-GEMMASCOPE-RES-131K
    7. 1254
    Prev
    Next
    INDEX
    Explanations

    providing environmental benefits and regulation

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

    phrases describing ecosystem services, benefits, and environmental resources.

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

    The main thing this neuron does is detect mentions of ecosystem “services” and related phrases describing the benefits nature provides.

    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
     océano
    -0.82
    zesse
    -0.82
    えました
    -0.79
    MSM
    -0.77
     inflammation
    -0.77
    cnico
    -0.75
     seaweed
    -0.75
     phun
    -0.75
    らく
    -0.74
     tuin
    -0.74
    POSITIVE LOGITS
     provide
    1.41
     oxygen
    1.36
     providing
    1.23
     shelter
    1.23
    提供
    1.21
     buffer
    1.17
     filter
    1.15
     filtering
    1.15
     Provide
    1.09
     regulating
    1.09
    Activations Density 0.043%

    No Known Activations