© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79121
    Prev
    Next
    INDEX
    Explanations

    greenhouse gas

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

    The neuron detects the phrase "greenhouse gas" and related terms in environmental and climate change contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    يران
    -0.75
    трите
    -0.71
     Chien
    -0.68
     Patients
    -0.67
     yarış
    -0.66
    ையில்
    -0.66
     setType
    -0.66
    ってい
    -0.66
     oyn
    -0.65
     cenu
    -0.65
    POSITIVE LOGITS
     gas
    2.92
     gases
    2.63
    Gas
    2.52
     Gas
    2.50
    gas
    2.23
     GAS
    1.88
    GAS
    1.88
     Gases
    1.88
     газо
    1.76
    ガス
    1.58
    Activations Density 0.023%

    No Known Activations