© 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. 47686
    Prev
    Next
    INDEX
    Explanations

    environmental protection and health

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

    content related to environmental topics, policies, and regulations.

    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
    檔
    -0.74
     Soccerway
    -0.73
    sels
    -0.73
    怎么做
    -0.72
    Huh
    -0.71
    niczy
    -0.71
    ᱙
    -0.70
    pera
    -0.69
     维
    -0.69
    });
    -0.69
    POSITIVE LOGITS
     environmental
    2.50
     Environmental
    2.20
    Environmental
    2.05
    environmental
    1.76
     pollution
    1.70
     environmentally
    1.59
     ENVIRONMENTAL
    1.58
     Pollution
    1.48
     cleaner
    1.44
    ENVIRONMENTAL
    1.41
    Activations Density 0.012%

    No Known Activations