© 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. 38501
    Prev
    Next
    INDEX
    Explanations

    thinking

    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
     alrededores
    -1.59
    Repost
    -1.47
    
    -1.46
    Pati
    -1.42
    人是
    -1.42
    ’.
    -1.41
     in
    -1.41
    铙
    -1.36
    Libra
    -1.36
    siswa
    -1.34
    POSITIVE LOGITS
     والف
    1.47
    end
    1.41
    aj
    1.38
    を教えて
    1.38
     entraîner
    1.33
    を活用
    1.33
     предприятия
    1.31
     WITH
    1.30
     travaillé
    1.30
    ay
    1.30
    Activations Density 0.014%

    No Known Activations