© 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. 1562
    Prev
    Next
    INDEX
    Explanations

    Swedish language or names

    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
     その
    1.40
     这
    1.35
     З
    1.30
     す
    1.28
    ດ້ານ
    1.28
    ᱜ
    1.26
    джа
    1.26
    获
    1.26
     この
    1.26
    ပ
    1.25
    POSITIVE LOGITS
     å
    2.12
     på
    2.07
     danske
    2.07
     Danmark
    2.06
     dansk
    2.00
     så
    1.99
     både
    1.98
     Å
    1.98
     Hø
    1.93
     norsk
    1.89
    Activations Density 0.248%

    No Known Activations