© 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. 62579
    Prev
    Next
    INDEX
    Explanations

    dialog boxes

    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
     echten
    -1.05
     fiatal
    -0.94
    投影
    -0.93
     normalen
    -0.93
     englischen
    -0.89
     damaligen
    -0.88
     zentralen
    -0.88
    čios
    -0.87
    ⾒
    -0.87
    GRAPHY
    -0.86
    POSITIVE LOGITS
    ues
    1.20
     box
    1.13
    Box
    1.13
     boxes
    1.05
    box
    0.97
    Boxes
    0.97
    ued
    0.96
     that
    0.96
    BOX
    0.94
     raison
    0.93
    Activations Density 0.008%

    No Known Activations