© 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. 10-GEMMASCOPE-RES-131K
    7. 99873
    Prev
    Next
    INDEX
    Explanations

    ozone and its effects

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

    references to ozone and related atmospheric chemistry terms.

    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_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
    -2.80
     Of
    -2.50
    the
    -2.30
    2
    -2.22
    在我的
    -2.20
    言う
    -2.20
    你要
    -2.17
    鸸
    -2.16
    いても
    -2.16
    也沒
    -2.14
    POSITIVE LOGITS
     ozone
    2.08
    东北
    2.05
    ↵↵
    1.94
     lidé
    1.84
    
    1.83
    
    1.80
     inventing
    1.78
    они
    1.77
    '@
    1.75
    南宫
    1.75
    Activations Density 0.011%

    No Known Activations