© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2280
    Prev
    Next
    INDEX
    Explanations

    wealth and educational inequalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     Kunden
    0.79
     Mankind
    0.78
     रिक्वायरमेंट
    0.76
     caos
    0.73
     ಬಳಕೆ
    0.72
     maniac
    0.71
    defence
    0.71
    询
    0.70
    保证金
    0.70
    принима
    0.69
    POSITIVE LOGITS
     inequality
    1.36
     median
    1.32
     desigualdad
    1.26
     disproportion
    1.24
     disparities
    1.24
     inequalities
    1.23
     Inequality
    1.23
    overty
    1.19
     poverty
    1.19
    Median
    1.18
    Activations Density 0.394%

    No Known Activations