© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    publication details and references

    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
    bukkit
    -0.84
     online
    -0.80
     memorials
    -0.76
     memorial
    -0.74
    Docs
    -0.73
    IEE
    -0.72
    音频
    -0.72
     blogs
    -0.71
    UiThread
    -0.71
     ceremonial
    -0.70
    POSITIVE LOGITS
     encyclo
    1.01
     encyclopedia
    1.01
    encyclo
    1.00
     DK
    0.98
     Toutes
    0.91
     ISBN
    0.89
    λογία
    0.86
     Editors
    0.85
     Haynes
    0.85
    ISBN
    0.79
    Activations Density 0.029%

    No Known Activations