© 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. 17-GEMMASCOPE-2-RES-16K
    7. 695
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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_17_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
    仍在
    1.01
    竭
    0.98
    很久
    0.92
    还在
    0.90
     fortement
    0.89
    antal
    0.88
    严重
    0.87
    தியின்
    0.86
     strongly
    0.86
    ҡ
    0.86
    POSITIVE LOGITS
     dàng
    1.43
     breezy
    1.14
    쉽
    1.05
     kolay
    0.97
     access
    0.91
     acess
    0.90
     accessibility
    0.90
     tarea
    0.89
     accesible
    0.88
     czynności
    0.88
    Activations Density 0.845%

    No Known Activations