© 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. 64279
    Prev
    Next
    INDEX
    Explanations

    other items or concepts

    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
     zowel
    -1.34
    both
    -1.14
     zarówno
    -1.13
    BOTH
    -1.06
     both
    -1.02
     febru
    -1.02
    त्व
    -1.00
     ambos
    -1.00
     and
    -0.99
     plik
    -0.98
    POSITIVE LOGITS
     other
    3.52
     lainnya
    2.88
    อื่น
    2.66
    其他
    2.52
     других
    2.22
     अन्य
    2.20
    其它
    2.13
     інших
    1.99
    other
    1.89
    的其他
    1.86
    Activations Density 0.086%

    No Known Activations