© 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. 56802
    Prev
    Next
    INDEX
    Explanations

    scientific notation scientific notation

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

    scientific notation with exponents, particularly numbers expressed in the format 10^x.

    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
     even
    -1.02
    Even
    -0.95
    Only
    -0.93
     reasonably
    -0.93
     corda
    -0.87
     purpose
    -0.86
    Year
    -0.85
    结
    -0.85
    They
    -0.83
     practically
    -0.83
    POSITIVE LOGITS
     historische
    0.86
     periodista
    0.85
    attempts
    0.84
     одежда
    0.83
     TWENTY
    0.82
     Eleven
    0.82
    chose
    0.81
     Nineteen
    0.79
    banez
    0.79
     dziew
    0.78
    Activations Density 0.012%

    No Known Activations