© 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. 22-GEMMASCOPE-RES-131K
    7. 127906
    Prev
    Next
    INDEX
    Explanations

    file paths and code

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     their
    -1.26
    ができます
    -1.23
     what
    -1.22
     it
    -1.14
    今夜
    -1.13
     enticing
    -1.04
    Shortly
    -1.02
     кало
    -1.02
     Před
    -1.01
     extraordinarily
    -0.99
    POSITIVE LOGITS
    があり
    1.26
    pekte
    1.12
    mediated
    1.09
    vereign
    1.06
    specific
    1.01
     maroc
    1.00
     dà
    1.00
    が
    0.99
     sfer
    0.96
    などは
    0.96
    Activations Density 0.006%

    No Known Activations