© 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. 458
    Prev
    Next
    INDEX
    Explanations

    South Africa, Sri Lanka, Ukraine

    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
    之前
    0.80
    before
    0.79
     сло
    0.77
    前面
    0.75
     s
    0.75
     почти
    0.74
     (
    0.73
     перед
    0.72
     more
    0.72
     набор
    0.70
    POSITIVE LOGITS
    ânia
    1.50
     Capitalism
    1.38
     capitalismo
    1.30
    ští
    1.26
    acán
    1.25
     autoridades
    1.24
    áles
    1.23
    ጵ
    1.22
     capitalist
    1.22
     Federation
    1.22
    Activations Density 0.293%

    No Known Activations