© 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. 48216
    Prev
    Next
    INDEX
    Explanations

    squamous cell carcinoma and Ringo Starr

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

    abbreviations in medical and technical contexts, particularly acronyms like "SCC".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is specialized to pick out occurrences of the uppercase acronym “SCC” (often paired with numbers or in parentheses).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     เพราะ
    -2.45
     stehenden
    -2.36
     好看
    -2.36
     ซึ่ง
    -2.30
    erintah
    -2.20
     gän
    -2.20
    甚至
    -2.16
    However
    -2.16
     gewiß
    -2.14
     achten
    -2.13
    POSITIVE LOGITS
    釹
    2.53
    }{
    2.53
    k
    2.48
    
    2.42
    饜
    2.42
     they
    2.38
     organismes
    2.36
    猻
    2.33
    着脸
    2.33
     sprüche
    2.33
    Activations Density 0.003%

    No Known Activations