© 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. 25059
    Prev
    Next
    INDEX
    Explanations

    part 5 college In SPECT Construction burnt Tomorrow Vijay

    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
    それから
    -1.12
    娯
    -1.11
    個人的には
    -1.08
     femininos
    -1.01
     problémy
    -1.01
    アップデート
    -1.01
    って思
    -0.96
    몹
    -0.95
    ieros
    -0.95
    oblo
    -0.94
    POSITIVE LOGITS
     and
    1.23
     gethan
    1.13
    IContainer
    1.06
     '';
    1.05
    ='';
    1.04
     Continued
    1.04
     mismas
    1.02
     два
    1.01
     Erzä
    0.99
     Grünen
    0.99
    Activations Density 0.233%

    No Known Activations