© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58346
    Prev
    Next
    INDEX
    Explanations

    LGBTQ identities

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

    This neuron detects mentions of LGBT equality or rights (e.g. “for the LGBT community,” “equality for LGBT persons,” etc.).

    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
    ])))
    -0.87
    KERNEL
    -0.82
    conos
    -0.76
    >>>>>>
    -0.75
    תודה
    -0.74
    ්‍
    -0.74
    >>>>>
    -0.71
    цуз
    -0.71
    roasted
    -0.71
    телю
    -0.71
    POSITIVE LOGITS
     LGBTQ
    4.44
     LGBT
    4.19
    LGBT
    3.78
     LGB
    3.14
     gay
    3.06
     lesbian
    2.77
     homosexual
    2.77
     queer
    2.73
     Lesbian
    2.67
     lgbt
    2.66
    Activations Density 0.065%

    No Known Activations