© 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. 22-GEMMASCOPE-RES-131K
    7. 25075
    Prev
    Next
    INDEX
    Explanations

    in vivo studies

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

    The neuron detects the phrase "in vivo" in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The main thing this neuron does is find the phrase “in vivo.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     остался
    -1.08
     دیگری
    -1.07
     Warhol
    -0.97
     Cochin
    -0.96
     henceforth
    -0.95
     STAY
    -0.91
    Thêm
    -0.91
    έχ
    -0.90
    继续
    -0.90
     Selma
    -0.90
    POSITIVE LOGITS
     practical
    1.21
     реаль
    1.16
     situations
    1.15
     applications
    1.13
     real
    1.11
     application
    1.06
    Practical
    1.00
     live
    0.96
     practice
    0.96
     AppColors
    0.94
    Activations Density 0.255%

    No Known Activations