© 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. 14832
    Prev
    Next
    INDEX
    Explanations

    sectors and industries

    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
     invent
    1.53
     civic
    1.53
    ge
    1.48
     Horticulture
    1.47
     Lavinia
    1.46
     Sita
    1.46
    园
    1.43
    KOM
    1.38
    地理
    1.38
    乡
    1.37
    POSITIVE LOGITS
    Medicare
    1.62
     notched
    1.59
    enched
    1.58
    iviato
    1.54
     capítulo
    1.52
    冠軍
    1.49
     штра
    1.48
     exponencial
    1.48
     nemoc
    1.47
    不禁
    1.46
    Activations Density 0.071%

    No Known Activations