© 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. 10625
    Prev
    Next
    INDEX
    Explanations

    ways or means

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    急
    0.86
     急
    0.85
     UTF
    0.83
     timezone
    0.81
     도착
    0.80
     hlavní
    0.80
    到着
    0.80
     여기가
    0.80
     丸
    0.80
     নায়
    0.79
    POSITIVE LOGITS
     analogy
    1.17
     osmosis
    1.12
    words
    1.08
     words
    1.05
    through
    1.04
     books
    1.04
     word
    1.04
     careful
    1.03
     através
    1.03
     attraverso
    1.03
    Activations Density 0.242%

    No Known Activations