© 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. 114067
    Prev
    Next
    INDEX
    Explanations

    offspring and siblings

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

    familial relationships like "daughters", "son", "nephew", "siblings", and "cousin" within biographical text.

    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
    蝋
    -1.73
    絶妙
    -1.66
    
    -1.60
    Otros
    -1.48
    ふわふわ
    -1.46
    莛
    -1.44
     tombé
    -1.43
    どこに
    -1.43
    푆
    -1.42
     verschieden
    -1.41
    POSITIVE LOGITS
     at
    2.19
     had
    2.06
     that
    1.67
     but
    1.56
     if
    1.48
     after
    1.47
     who
    1.47
     have
    1.45
     should
    1.42
    ７
    1.41
    Activations Density 0.005%

    No Known Activations