© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65254
    Prev
    Next
    INDEX
    Explanations

    equality and equal treatment

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

    The neuron detects formal legal and institutional terminology—names of government bodies, commissions, acts, and other official references concerning equality or anti-discrimination.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Congressional
    -0.76
     ایر
    -0.71
    lask
    -0.71
    hedra
    -0.71
     Medik
    -0.69
     japon
    -0.69
    ляю
    -0.69
    }^
    -0.69
    ticons
    -0.69
    })(
    -0.67
    POSITIVE LOGITS
     equality
    1.32
     Equality
    1.14
    Eq
    1.14
    Equality
    1.14
     EHR
    0.96
    equality
    0.93
     equ
    0.92
     Equ
    0.88
    eq
    0.87
     Eq
    0.85
    Activations Density 0.018%

    No Known Activations