© 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-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9659
    Prev
    Next
    INDEX
    Explanations

    online courses and learning platforms

    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
     Mej
    0.94
    Dib
    0.85
    idl
    0.84
    Problem
    0.83
    Occ
    0.82
     இணைய
    0.82
     Problem
    0.82
     失
    0.80
     dimiliki
    0.80
    diabetes
    0.80
    POSITIVE LOGITS
     conjunto
    1.01
     tegas
    0.92
     conjuntos
    0.90
     heran
    0.90
    рун
    0.89
    時短
    0.89
    более
    0.88
     kompak
    0.88
     kata
    0.87
     berharap
    0.87
    Activations Density 0.004%

    No Known Activations