© 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. 10682
    Prev
    Next
    INDEX
    Explanations

    electrical wiring bundles

    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
     đậu
    0.90
     saucer
    0.89
    crash
    0.87
    颧
    0.85
     lid
    0.84
     crash
    0.84
     ActionListener
    0.84
     lids
    0.84
     Moz
    0.84
     Mifflin
    0.83
    POSITIVE LOGITS
     Cable
    1.50
     cable
    1.48
    撚
    1.48
     cables
    1.41
     braid
    1.40
     strands
    1.39
     бух
    1.37
    巻き
    1.36
     spool
    1.35
    Cable
    1.35
    Activations Density 0.355%

    No Known Activations