© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 831
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    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
     চেয়ারম্যান
    2.47
     |_{
    2.19
     yě
    1.99
    Numerator
    1.99
    setProgress
    1.99
    Military
    1.97
    𝐳
    1.97
    Conversely
    1.90
    /**',
    1.88
     cmd
    1.87
    POSITIVE LOGITS
    izacja
    2.22
    Globe
    2.00
     Globe
    1.96
    ニング
    1.84
    othi
    1.84
    eliness
    1.84
     کاسینو
    1.77
     घण्ट
    1.76
    idase
    1.74
    ophilic
    1.73
    Activations Density 0.787%

    No Known Activations