© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10515
    Prev
    Next
    INDEX
    Explanations

    bias, discrimination, prejudice

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on words referring to social injustices—particularly discrimination, bias, and systemic inequalities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     keselamatan
    0.76
     fren
    0.59
     vesc
    0.57
     httpClient
    0.55
    τέρα
    0.55
    聒
    0.55
     frantically
    0.54
    🧨
    0.54
     frantic
    0.54
     bezpeč
    0.54
    POSITIVE LOGITS
     discriminatory
    2.44
     discrimination
    2.42
     Discrimination
    2.27
    discrimination
    2.13
     discrim
    2.11
     racism
    2.09
     Discrimin
    2.09
     discrimin
    2.03
     inequalities
    2.00
    discrimin
    2.00
    Activations Density 0.289%

    No Known Activations