© 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. 22-GEMMASCOPE-RES-131K
    7. 14943
    Prev
    Next
    INDEX
    Explanations

    pollution and contamination

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

    references to pollution, contamination, and environmental damage.

    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_22/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
    没有
    -2.80
    u
    -2.27
    .”
    -1.98
    基本上
    -1.95
    Ｊ
    -1.93
     manejo
    -1.90
    IN
    -1.90
    如同
    -1.89
    ين
    -1.88
    。
    -1.87
    POSITIVE LOGITS
    ↵
    2.36
    轫
    2.30
    }
    2.11
    
    2.03
     spacious
    1.99
    鈇
    1.98
    之类的
    1.95
    聼
    1.92
     slechts
    1.87
    zelfde
    1.87
    Activations Density 0.019%

    No Known Activations