© 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. 58240
    Prev
    Next
    INDEX
    Explanations

    code, questions, and actions

    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
    Again
    -1.74
     снова
    -1.72
    真的好
    -1.67
     ceux
    -1.66
    她
    -1.64
     tych
    -1.63
     Hinblick
    -1.56
    ties
    -1.55
    它的
    -1.55
     but
    -1.54
    POSITIVE LOGITS
     where
    1.70
     this
    1.57
    瑧
    1.47
    諍
    1.45
    揶
    1.45
    代わりに
    1.45
     सत्यापित
    1.45
    発言
    1.42
     lagar
    1.41
    掟
    1.41
    Activations Density 0.007%

    No Known Activations