© 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. 65816
    Prev
    Next
    INDEX
    Explanations

    LGBTQ+ community and gay rights

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    AMG
    -0.86
    ñora
    -0.84
    FileInputStream
    -0.80
    减
    -0.79
     skolan
    -0.78
    citep
    -0.78
    Plugins
    -0.78
    jvm
    -0.76
     озе
    -0.74
     redox
    -0.73
    POSITIVE LOGITS
     gay
    3.78
     LGBT
    3.64
     LGBTQ
    3.45
    LGBT
    3.33
     queer
    3.27
    gay
    3.19
     Gay
    3.06
     gays
    3.06
     homosexual
    3.05
     Queer
    2.86
    Activations Density 0.243%

    No Known Activations