© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45567
    Prev
    Next
    INDEX
    Explanations

    transgender and sexual minorities

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

    The neuron fires on tokens that name sexual orientations or gender identities (e.g. heterosexual, homosexual, bisexual, asexual, gay, lesbian, transgender).

    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
     transition
    -1.80
     Transition
    -1.73
    Transition
    -1.73
    transition
    -1.59
     transitions
    -1.45
    Transitions
    -1.24
     transitioned
    -1.23
     Transitions
    -1.23
    transitions
    -1.17
     transitioning
    -1.13
    POSITIVE LOGITS
     asexual
    1.47
     arom
    1.28
     transgender
    1.25
    romantic
    1.22
    flux
    1.20
     Aromatic
    0.99
     Aro
    0.98
     aromatic
    0.97
     AVEN
    0.97
     ace
    0.96
    Activations Density 0.022%

    No Known Activations