© 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. 32673
    Prev
    Next
    INDEX
    Explanations

    $( or (

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     estableció
    -0.94
     obtuvo
    -0.93
     contaba
    -0.93
     preciso
    -0.90
    溼
    -0.89
    ___]
    -0.89
    effic
    -0.88
    みよう
    -0.88
    见面
    -0.87
    젊
    -0.87
    POSITIVE LOGITS
     your
    1.16
    processable
    0.95
     даже
    0.93
     навіть
    0.93
    乂
    0.90
    FilterChain
    0.90
     opak
    0.89
     each
    0.89
    chov
    0.89
     extrême
    0.87
    Activations Density 0.008%

    No Known Activations