© 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. 373
    Prev
    Next
    INDEX
    Explanations

    FORT WORTH

    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
    AppBar
    -1.02
     comerci
    -0.96
     negatif
    -0.93
     porcelana
    -0.92
     metálico
    -0.90
     persil
    -0.89
     found
    -0.88
     kapan
    -0.87
     térmico
    -0.86
     inesperado
    -0.86
    POSITIVE LOGITS
     Теперь
    1.10
     asimismo
    1.03
    értelmű
    1.01
     Considerable
    0.98
     중요
    0.94
    足以
    0.93
     biex
    0.93
    ることができます
    0.93
     Даже
    0.91
     myriad
    0.91
    Activations Density 0.001%

    No Known Activations