© 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. 106105
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     vaccination
    -1.40
     vaccinated
    -1.27
     vaccine
    -1.18
    Vaccination
    -1.16
     vaccines
    -1.16
     vaccinations
    -1.15
    vaccinated
    -1.15
     Biden
    -1.12
     NFTs
    -1.09
    Vaccine
    -1.06
    POSITIVE LOGITS
     Redskins
    0.87
     coronal
    0.77
     discography
    0.75
    꿈
    0.74
     DKI
    0.73
     SDN
    0.72
    🧻
    0.72
    etra
    0.71
     Plated
    0.71
     Xs
    0.71
    Activations Density 0.017%

    No Known Activations