© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83999
    Prev
    Next
    INDEX
    Explanations

    proteins, medical abbreviations

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

    uppercase letter pairs or acronyms in technical or scientific text.

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

    The neuron is detecting uppercase acronyms and initialisms (e.g., TLIF, PTEN, MMIC).

    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
     Roughly
    -3.05
     In
    -2.75
     Of
    -2.66
     Presumably
    -2.59
    This
    -2.58
     Both
    -2.48
     Theore
    -2.48
     Because
    -2.47
     После
    -2.47
    Of
    -2.39
    POSITIVE LOGITS
    s
    3.88
    饪
    2.91
    鱨
    2.66
    葑
    2.64
    蔸
    2.63
    詎
    2.63
    的
    2.59
    ꜄
    2.58
    鼍
    2.52
     navn
    2.50
    Activations Density 0.078%

    No Known Activations