© 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. 364
    Prev
    Next
    INDEX
    Explanations

    healing injuries and wounds

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

    words and phrases related to healing, recovery, or wound healing.

    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
    ፨
    -2.92
    鲀
    -2.83
    ༀ
    -2.80
    趼
    -2.78
    
    -2.75
    祤
    -2.66
    ⤥
    -2.52
    嵎
    -2.50
    迓
    -2.42
    ⤞
    -2.42
    POSITIVE LOGITS
    {
    3.44
    是
    3.33
    E
    2.86
    有
    2.81
    O
    2.77
    的
    2.58
    4
    2.52
    C
    2.50
    或是
    2.47
    B
    2.44
    Activations Density 0.003%

    No Known Activations