© 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. 92055
    Prev
    Next
    INDEX
    Explanations

    hydrogen, fuel cells, clean energy

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

    references to energy sources, fuels, and industrial chemicals.

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

    This neuron responds to technical energy and environmental terms—especially occurrences of “CO₂,” “carbon,” “neutral,” and related jargon—signaling discussions of carbon-neutral or CO₂-removal processes.

    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
     Skype
    -1.34
    http
    -1.11
     http
    -0.96
    hogs
    -0.91
     ২০১
    -0.87
    ❣
    -0.87
     skype
    -0.86
    هنگ
    -0.86
    Obama
    -0.86
    Skype
    -0.84
    POSITIVE LOGITS
     hydrogen
    1.78
    hydrogen
    1.48
     Hydrogen
    1.28
     Wasserstoff
    1.21
     electroly
    1.21
    Hydrogen
    1.18
     decarbon
    1.09
     ESG
    1.08
     Biden
    1.00
     carbon
    0.99
    Activations Density 0.009%

    No Known Activations