© 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. 48269
    Prev
    Next
    INDEX
    Explanations

    Kawasaki disease, basal cell carcinoma

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

    brand names and technical terminology related to medicine, pharmacology, and technology.

    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
    n
    -3.39
    1
    -2.88
    8
    -2.80
    one
    -2.77
    4
    -2.58
    3
    -2.50
    7
    -2.48
    就像是
    -2.45
    ’
    -2.36
    2
    -2.31
    POSITIVE LOGITS
    釭
    2.83
    硨
    2.77
    
    2.73
    」，
    2.69
    ❔
    2.53
     ehem
    2.52
    
    2.44
    鼇
    2.41
    糴
    2.41
    〮
    2.39
    Activations Density 0.002%

    No Known Activations