© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6355
    Prev
    Next
    INDEX
    Explanations

    cultural sensitivity and diversity

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

    The neuron fires on mentions of social‐justice and political‐activism topics (e.g., white privilege, racial justice, 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
     businessmen
    0.88
     retarded
    0.71
    􀂃
    0.71
    :-)
    0.71
     salesmen
    0.70
    
    0.70
    http
    0.68
     retardation
    0.66
    
    0.66
     Ruman
    0.64
    POSITIVE LOGITS
     LGBTQ
    2.00
     Racial
    1.84
     racial
    1.74
     racially
    1.69
     Indigenous
    1.65
     Racism
    1.64
     inclusivity
    1.64
     queer
    1.62
     Queer
    1.59
     racism
    1.52
    Activations Density 0.393%

    No Known Activations