© 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. 41699
    Prev
    Next
    INDEX
    Explanations

    EIA, CEA, agri, biliary

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

    acronyms and abbreviations related to scientific, medical, and technical terminology.

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

    The neuron detects uppercase acronyms and specialized codes (e.g. EIA, CEA, Agri) in the text.

    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
    нутри
    -2.53
    \
    -2.52
     面包
    -2.50
    :{
    -2.48
    ਞ
    -2.39
    썽
    -2.38
    욤
    -2.34
     企业
    -2.30
    "}}>
    -2.30
    цию
    -2.28
    POSITIVE LOGITS
        
    2.53
    他对
    2.41
    ing
    2.39
    ですので
    2.39
    独特的
    2.34
     была
    2.33
    所说的
    2.28
     untuk
    2.22
    replyreport
    2.17
    久し
    2.14
    Activations Density 0.005%

    No Known Activations