© 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. 64578
    Prev
    Next
    INDEX
    Explanations

    product models and locations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     които
    -1.38
     която
    -1.34
    の人に
    -1.24
    で大
    -1.23
    に行って
    -1.23
    に入れる
    -1.20
    umbai
    -1.20
    
    -1.19
     desarrollado
    -1.19
     muñecas
    -1.18
    POSITIVE LOGITS
     ATTR
    0.98
    <bos>
    0.94
    ecé
    0.90
     фло
    0.88
     yong
    0.86
    Alone
    0.86
    ？』
    0.85
    dish
    0.85
    ряд
    0.84
     hati
    0.84
    Activations Density 0.165%

    No Known Activations