© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70534
    Prev
    Next
    INDEX
    Explanations

    Types, why, benefits

    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
     on
    -1.27
     at
    -1.05
    になったら
    -0.99
    顫
    -0.98
    beiten
    -0.97
    честву
    -0.97
    CONCLUSION
    -0.95
    CONCLUSIONS
    -0.94
     dela
    -0.94
    یدا
    -0.92
    POSITIVE LOGITS
     oração
    1.14
    主要的
    1.10
    Types
    1.09
     there
    1.09
     Vorteile
    1.05
     Types
    1.01
     podemos
    1.00
     überprü
    0.99
     asistir
    0.97
     why
    0.97
    Activations Density 0.041%

    No Known Activations