© 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. 58339
    Prev
    Next
    INDEX
    Explanations

    medical and scientific acronyms

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

    acronyms and abbreviations in technical or scientific contexts.

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

    The neuron activates on sequences of consecutive uppercase letters—i.e. acronyms or initialisms.

    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
    兩
    -1.38
    entuk
    -1.36
     who
    -1.34
    although
    -1.26
     although
    -1.24
    髣
    -1.21
     staunch
    -1.18
    を変える
    -1.16
     acestei
    -1.16
    SEGUIR
    -1.14
    POSITIVE LOGITS
    =
    1.32
     its
    1.28
     realmente
    1.26
     jego
    1.19
    "'
    1.18
    제
    1.12
    お楽しみに
    1.11
    ".
    1.10
     événement
    1.09
     siècles
    1.09
    Activations Density 0.372%

    No Known Activations