© 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. 918
    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
    Thor
    0.91
     Weir
    0.88
     desag
    0.88
     Rockstar
    0.85
     Bein
    0.84
    驯
    0.83
     Siri
    0.82
     Niko
    0.80
     consensual
    0.79
    twitch
    0.79
    POSITIVE LOGITS
     paper
    2.47
     printer
    2.44
     printing
    2.43
     printers
    2.38
    印刷
    2.35
    用紙
    2.30
     Printing
    2.28
     kertas
    2.27
     photocopy
    2.23
    纸
    2.22
    Activations Density 3.418%

    No Known Activations