© 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. 32568
    Prev
    Next
    INDEX
    Explanations

    heaven and earth transitions

    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
    DeclareMath
    -1.17
     definiert
    -1.03
     nadru
    -1.00
    וּ
    -0.99
    loé
    -0.97
     günü
    -0.96
     Chrift
    -0.94
     These
    -0.91
     Finally
    -0.91
    擔心
    -0.90
    POSITIVE LOGITS
     his
    1.20
     творо
    1.17
     there
    1.13
     ингреди
    1.09
     картофе
    1.09
    żdy
    1.09
     better
    1.07
    プローチ
    1.02
     our
    1.02
    >{"
    0.98
    Activations Density 0.003%

    No Known Activations