© 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. 29928
    Prev
    Next
    INDEX
    Explanations

    eds or ed

    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
     bezeich
    -0.99
     those
    -0.95
    馀
    -0.91
     sichere
    -0.90
     notwendi
    -0.87
    直至
    -0.87
    jbl
    -0.85
     Киє
    -0.84
     necesitaba
    -0.84
    梟
    -0.84
    POSITIVE LOGITS
     eds
    1.69
     Eds
    1.28
    eds
    1.18
     coord
    1.18
     ed
    1.14
    Ꭾ
    1.02
     uur
    1.01
     triomphe
    1.00
     doigt
    0.99
     реда
    0.95
    Activations Density 0.015%

    No Known Activations