© 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. 34-GEMMASCOPE-RES-131K
    7. 47299
    Prev
    Next
    INDEX
    Explanations

    academic science subjects

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

    academic disciplines and scientific fields, particularly related to science, mathematics, and physics.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     economists
    -1.01
    惆
    -0.89
     economist
    -0.83
     antidepressants
    -0.82
     psychiatrists
    -0.78
    ɳ
    -0.76
    !”
    -0.75
     canciones
    -0.75
    psychiat
    -0.74
    economic
    -0.73
    POSITIVE LOGITS
     science
    2.88
     physics
    2.61
     biology
    2.42
     chemistry
    2.38
     Science
    2.33
     Biology
    2.30
     Physics
    2.28
     Chemistry
    2.17
    Physics
    2.16
    science
    2.02
    Activations Density 0.054%

    No Known Activations