© 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. 10-GEMMASCOPE-RES-131K
    7. 20636
    Prev
    Next
    INDEX
    Explanations

    environmental policy and concerns

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

    phrases related to environmental protection and regulatory policies addressing environmental issues.

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

    The neuron strongly activates on the term “environmental” (especially in phrases like “environmental protection,” “environmental regulations,” etc.), indicating it detects references to environmental topics.

    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
    ");
    -1.67
    ين
    -1.48
     Izuku
    -1.45
     implor
    -1.43
    i
    -1.39
    ሖ
    -1.38
    鋨
    -1.38
     incred
    -1.34
    Appellee
    -1.34
     versed
    -1.34
    POSITIVE LOGITS
     and
    2.14
     it
    1.89
     combined
    1.47
     \
    1.45
    THERS
    1.42
    we
    1.41
     coupled
    1.37
     stuff
    1.35
     denaro
    1.34
     without
    1.30
    Activations Density 0.021%

    No Known Activations