© 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. 85474
    Prev
    Next
    INDEX
    Explanations

    deoxy compounds and detoxification treatments

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

    chemical or pharmaceutical terms, particularly those with prefixes like "deoxy" or related to detoxification processes.

    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
    ar
    -2.81
    る
    -2.58
    ть
    -2.52
    
    -2.36
    上が
    -2.28
    o
    -2.27
    ii
    -2.25
    寕
    -2.25
    ↵
    -2.20
    又在
    -2.20
    POSITIVE LOGITS
    I
    2.73
    ﮩ
    2.69
    ]
    2.61
    ";//
    2.50
    粂
    2.42
    基本的
    2.39
    ">
    2.36
    uſe
    2.34
    });
    2.28
     夾
    2.28
    Activations Density 0.009%

    No Known Activations