© 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. 106365
    Prev
    Next
    INDEX
    Explanations

    Nintendo, Texas Instruments, hardware

    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
     пост
    -0.87
     Богу
    -0.85
    산
    -0.74
     soltar
    -0.71
    ниците
    -0.71
    ܘ
    -0.71
     ПК
    -0.69
     gustan
    -0.69
     mesos
    -0.68
    angé
    -0.68
    POSITIVE LOGITS
     Voyage
    1.02
    Voyage
    0.89
     TI
    0.88
     voyage
    0.86
    TI
    0.77
    voyage
    0.75
    Semoga
    0.75
     Tir
    0.73
    roduction
    0.71
    вёр
    0.71
    Activations Density 0.033%

    No Known Activations