© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4653
    Prev
    Next
    INDEX
    Explanations

    alternative viewpoints and differing actions

    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_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
     whatnot
    1.68
     kinda
    1.60
     Json
    1.48
     Tuple
    1.42
     idk
    1.39
     lmao
    1.35
     Binance
    1.35
     :/
    1.34
    ต่างๆ
    1.33
     Cpu
    1.32
    POSITIVE LOGITS
    著名
    1.06
     pioneering
    1.01
    inu
    1.00
    鼓励
    1.00
    生涯
    0.98
     critical
    0.98
    标志
    0.97
    一生
    0.95
     sharply
    0.94
    critical
    0.94
    Activations Density 0.609%

    No Known Activations