© 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. 10-GEMMASCOPE-RES-131K
    7. 83695
    Prev
    Next
    INDEX
    Explanations

    titles and names

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Aseg
    -1.77
     Ofrece
    -1.65
     Asegúrese
    -1.63
    amerikanischer
    -1.57
    𖥧
    -1.55
    ܜ
    -1.52
     bytu
    -1.48
     parku
    -1.46
     voltak
    -1.46
    wki
    -1.45
    POSITIVE LOGITS
     again
    1.55
     about
    1.49
    0
    1.48
    7
    1.46
    5
    1.45
    4
    1.43
    _{
    1.42
     =
    1.42
     further
    1.41
    2
    1.38
    Activations Density 0.004%

    No Known Activations