© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14989
    Prev
    Next
    INDEX
    Explanations

    medical related terms

    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_7_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
    grams
    1.52
    ｳ
    1.50
    丢失
    1.40
    
    1.37
    bells
    1.37
    classes
    1.37
    Peso
    1.36
    arrest
    1.36
    offensive
    1.36
     psicología
    1.34
    POSITIVE LOGITS
     कड
    1.46
     enclose
    1.45
     함께
    1.44
    ंनी
    1.41
     yra
    1.41
     Existem
    1.39
    葢
    1.38
     teilen
    1.38
     existem
    1.35
     operates
    1.34
    Activations Density 0.037%

    No Known Activations