© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 732
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     त्यानुसार
    0.78
     আবির্ভাব
    0.76
     আগ্রহী
    0.76
    الة
    0.75
     Unterschiede
    0.75
     откло
    0.74
     masing
    0.74
    症
    0.73
    слежи
    0.73
    нали
    0.73
    POSITIVE LOGITS
     livelihoods
    1.90
     innocent
    1.73
     irreplaceable
    1.70
     irrepar
    1.63
     delicate
    1.55
     priceless
    1.55
     lives
    1.55
     innoc
    1.52
     livelihood
    1.49
     fragile
    1.48
    Activations Density 1.948%

    No Known Activations