© 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. 6930
    Prev
    Next
    INDEX
    Explanations

    death and dying circumstances

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

    references to death, dying, or passing away.

    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
     вроде
    -1.43
    崽
    -1.43
     varje
    -1.41
    либо
    -1.38
     into
    -1.36
     first
    -1.36
    过来了
    -1.35
     provenientes
    -1.30
    efits
    -1.28
     такие
    -1.26
    POSITIVE LOGITS
     eki
    1.70
    ICALLY
    1.66
     motore
    1.61
     different
    1.48
     druga
    1.48
     textView
    1.48
     lampada
    1.48
     اسلامی
    1.45
    scrollY
    1.45
    ſtra
    1.44
    Activations Density 0.034%

    No Known Activations