© 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. 3604
    Prev
    Next
    INDEX
    Explanations

    life-threatening conditions or outcomes

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

    The neuron detects phrases referring to "life-threatening" conditions or situations in medical and safety contexts.

    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
    皲
    -1.99
     faſt
    -1.98
    釙
    -1.91
     ..............
    -1.88
     ¨
    -1.88
     เมื่อ
    -1.84
    fordable
    -1.84
     MASSACHUSETTS
    -1.81
     ALLE
    -1.80
     ROOMS
    -1.78
    POSITIVE LOGITS
     and
    2.14
    这不是
    2.09
     /
    2.06
    糅
    1.95
     That
    1.92
    ～～
    1.85
     Wirken
    1.84
     Handeln
    1.80
     or
    1.79
    謄
    1.76
    Activations Density 0.008%

    No Known Activations