© 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. 32801
    Prev
    Next
    INDEX
    Explanations

    modern concepts associated with education and society

    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
     triko
    -1.16
    zegor
    -1.06
     BoxDecoration
    -1.06
     mediocre
    -1.05
     döner
    -1.02
    へん
    -1.02
     geweldige
    -1.02
     bry
    -1.01
     bijzondere
    -1.01
     kollu
    -0.99
    POSITIVE LOGITS
     modern
    1.91
     modernity
    1.37
     Western
    1.32
    modern
    1.30
     Modern
    1.28
     more
    1.26
     moderna
    1.23
     their
    1.23
    现代
    1.21
     new
    1.20
    Activations Density 0.040%

    No Known Activations