© 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. 34-GEMMASCOPE-RES-131K
    7. 117821
    Prev
    Next
    INDEX
    Explanations

    degree of burn

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

    mentions of burns and burn-related injuries or treatments.

    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_34/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
    コク
    -0.77
     Negeri
    -0.75
     Vang
    -0.75
    ousine
    -0.71
    capsulation
    -0.69
     menstru
    -0.68
     parag
    -0.67
     periodi
    -0.66
    oxford
    -0.66
     codzien
    -0.65
    POSITIVE LOGITS
     burns
    3.77
     burn
    3.41
     burned
    3.11
     burnt
    2.81
     Burn
    2.73
    burns
    2.70
    Burn
    2.67
     Burns
    2.64
    burn
    2.58
    Burns
    2.55
    Activations Density 0.053%

    No Known Activations