© 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-16K
    7. 1974
    Prev
    Next
    INDEX
    Explanations

    nationalistic expansionism

    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
     surrounded
    1.03
     buoy
    1.01
     pleasantly
    1.01
     intuition
    0.97
     sandwiched
    0.96
     hoping
    0.96
     inundated
    0.96
    傍
    0.94
     wrapped
    0.93
     Surrounded
    0.93
    POSITIVE LOGITS
     misconduct
    1.95
     wrongdoing
    1.85
     violations
    1.69
     unlawful
    1.67
     immoral
    1.66
     mismanagement
    1.64
     infring
    1.64
    違反
    1.63
     unfair
    1.59
     unethical
    1.58
    Activations Density 0.912%

    No Known Activations