© 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. 38699
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

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

    The neuron detects technical abbreviations, acronyms, and specialized code identifiers that often appear in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -3.20
     and
    -2.86
     as
    -2.70
     because
    -2.63
     after
    -2.44
    Also
    -2.33
     from
    -2.33
     Also
    -2.30
     After
    -2.27
     new
    -2.17
    POSITIVE LOGITS
    意外と
    2.08
     sooo
    1.95
    マジで
    1.95
     insanely
    1.91
     hordes
    1.90
    シャレ
    1.89
     soooo
    1.88
     siè
    1.84
     tetrachloride
    1.83
     myriad
    1.80
    Activations Density 0.226%

    No Known Activations