© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110792
    Prev
    Next
    INDEX
    Explanations

    medical and scientific abbreviations

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

    medical and scientific abbreviations or acronyms in parentheses.

    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
     though
    -1.13
     this
    -1.04
     Werkstatt
    -1.00
    questionnaire
    -1.00
     while
    -0.98
     didel
    -0.97
    Although
    -0.96
     whether
    -0.96
     Brücke
    -0.96
     pasirink
    -0.95
    POSITIVE LOGITS
    velg
    1.27
    ChangeEvent
    1.18
     pleadings
    1.16
    vät
    1.14
     лютого
    1.13
     tevé
    1.13
    Тема
    1.10
    CreateModel
    1.09
     emballage
    1.09
    ៌
    1.07
    Activations Density 0.484%

    No Known Activations