© 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-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4890
    Prev
    Next
    INDEX
    Explanations

    social justice and equity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spermatozoa
    0.81
    𝓮
    0.78
     controvers
    0.75
     portavoz
    0.74
     आतंकवाद
    0.73
     personalità
    0.73
     Sert
    0.73
     endeavours
    0.73
    ^_^
    0.72
     controversial
    0.71
    POSITIVE LOGITS
     equity
    1.11
     Equity
    1.11
    Equity
    1.10
     EQUITY
    1.06
    equity
    0.96
     justice
    0.94
     decar
    0.93
     Justice
    0.93
     justicia
    0.91
    Justice
    0.85
    Activations Density 0.095%

    No Known Activations