© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57987
    Prev
    Next
    INDEX
    Explanations

    environmentally friendly

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

    words or phrases containing "eco-friendly" and related ecological terms.

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

    The neuron activates on hyphenated “eco-” adjectives—especially the phrase “eco-friendly.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    锨
    -2.58
    岨
    -2.41
    嚶
    -2.36
    趼
    -2.30
    犼
    -2.28
    伥
    -2.22
     Meille
    -2.20
     Infór
    -2.19
     utilizan
    -2.14
     帅气
    -2.14
    POSITIVE LOGITS
    ]
    3.38
    {
    2.86
    *
    2.64
     thinks
    2.36
    d
    2.30
    w
    2.25
     was
    2.23
    (
    2.22
    v
    2.20
    t
    2.19
    Activations Density 0.009%

    No Known Activations