© 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. 83631
    Prev
    Next
    INDEX
    Explanations

    SMT SMT CFD TLR aortic

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

    abbreviations and acronyms like "SOA", "SMT", "ADT", often in technical or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    0
    -2.53
    8
    -2.28
    3
    -2.28
    but
    -2.22
     was
    -2.08
    2
    -2.05
     Он
    -2.03
    after
    -2.03
    it
    -2.02
     Азии
    -2.00
    POSITIVE LOGITS
    
    2.56
    ⬮
    2.31
    ？】
    2.31
    
    2.09
     neue
    2.08
     情侣
    2.06
     he
    2.05
    ࿙
    2.05
     compris
    2.02
    antaranya
    2.02
    Activations Density 0.012%

    No Known Activations