© 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. 25011
    Prev
    Next
    INDEX
    Explanations

    Nazi Germany and Hitler

    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
     these
    -1.64
    The
    -1.39
    $
    -1.30
    laszt
    -1.20
    这些
    -1.19
     Wör
    -1.19
     acrylique
    -1.18
     Reiche
    -1.16
    ;">
    -1.15
    Y
    -1.15
    POSITIVE LOGITS
    挎
    1.15
     Fähigkeiten
    1.14
    DAFTAR
    1.14
     Ergänzung
    1.13
     церковь
    1.13
     planea
    1.10
    ﻨ
    1.10
     Merkmale
    1.10
    tellingen
    1.10
    گیرد
    1.10
    Activations Density 0.020%

    No Known Activations