© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12071
    Prev
    Next
    INDEX
    Explanations

    saturated and unsaturated fats

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

    chemical terms related to fatty acids and lipids.

    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
     Ahnung
    -2.58
    躋
    -2.52
     selben
    -2.22
    然后
    -2.17
    是
    -2.13
    ሖ
    -2.03
     ardour
    -2.00
    他
    -1.93
    价格
    -1.92
    蕷
    -1.92
    POSITIVE LOGITS
     finely
    2.14
     specially
    1.97
    觏
    1.96
    采用了
    1.88
    套路
    1.88
     男士
    1.87
    ୌ
    1.84
    鄠
    1.80
     facilitating
    1.77
     ―
    1.77
    Activations Density 0.011%

    No Known Activations