© 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. 62486
    Prev
    Next
    INDEX
    Explanations

    names starting with John or Initials

    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
     contactez
    -0.75
     היום
    -0.71
    架构
    -0.69
    ulents
    -0.69
    phil
    -0.69
    ểu
    -0.68
     Apalagi
    -0.66
    pulsera
    -0.66
     особли
    -0.66
     Defects
    -0.65
    POSITIVE LOGITS
     identificar
    0.72
     Kyr
    0.68
     DCE
    0.66
    nameof
    0.66
     bilhões
    0.65
     Karachi
    0.65
     reportedly
    0.64
     Yamato
    0.63
     przyp
    0.63
     steigt
    0.63
    Activations Density 0.044%

    No Known Activations