© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 16378
    Prev
    Next
    INDEX
    Explanations

    hole or opening

    np_acts-logits-general · gemini-2.5-flash-lite

    holes and openings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
     modeli
    0.49
     modelli
    0.48
    зо
    0.47
     müş
    0.47
    퀀
    0.46
    飄
    0.46
    ίας
    0.46
    ईन
    0.46
    rolle
    0.45
     Datensch
    0.45
    POSITIVE LOGITS
     holes
    1.37
     отверсти
    1.31
     hole
    1.28
     Hole
    1.23
    穴
    1.22
    hole
    1.16
    holes
    1.06
     Holes
    1.06
     छेद
    0.95
    孔
    0.94
    Activations Density 0.953%

    No Known Activations