© 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. 34-GEMMASCOPE-RES-131K
    7. 56895
    Prev
    Next
    INDEX
    Explanations

    drawing conclusions

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dueño
    -0.92
     menggambarkan
    -0.90
     INFORMATION
    -0.90
     memahami
    -0.88
    adamia
    -0.86
    ímetro
    -0.85
     fundador
    -0.85
    čan
    -0.83
    continue
    -0.83
     Nachdem
    -0.82
    POSITIVE LOGITS
     conclusions
    2.41
     conclusion
    1.93
     Conclusions
    1.91
    Conclusions
    1.87
     concluding
    1.75
     Conclusion
    1.52
    CONCLUSIONS
    1.50
     заклю
    1.41
     conclude
    1.41
     Concluding
    1.36
    Activations Density 0.017%

    No Known Activations