© 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. 34-GEMMASCOPE-RES-131K
    7. 93676
    Prev
    Next
    INDEX
    Explanations

    washing machines and dishwashers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     possessive
    -0.82
    糊
    -0.76
     costante
    -0.76
     fouling
    -0.76
     térmico
    -0.75
     Himo
    -0.73
     nationalists
    -0.73
    cademy
    -0.73
     necks
    -0.73
    ляю
    -0.72
    POSITIVE LOGITS
     drum
    1.38
     detergent
    1.20
     bleach
    1.08
     washer
    1.04
    drum
    1.01
     giặt
    1.00
     drain
    0.98
     agit
    0.94
     clothes
    0.94
     garment
    0.93
    Activations Density 0.014%

    No Known Activations