© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2641
    Prev
    Next
    INDEX
    Explanations

    understanding prompts and context

    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_13_width_65k_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
     tarih
    1.23
    大陆
    1.13
     ROC
    1.08
    賀
    1.07
     bệnh
    1.07
     yani
    1.06
    omány
    1.03
    ởi
    1.03
     نحن
    1.03
    恕
    1.03
    POSITIVE LOGITS
     alone
    0.94
     helped
    0.87
     lessened
    0.85
     dictate
    0.85
     afforded
    0.84
     resulted
    0.82
    alone
    0.82
     leachate
    0.79
     enabled
    0.78
     ทำให้
    0.78
    Activations Density 0.510%

    No Known Activations