© 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. 65912
    Prev
    Next
    INDEX
    Explanations

    gay and marriage

    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
     prédio
    -0.85
     LGBT
    -0.80
     lgbt
    -0.79
     LGBTQ
    -0.75
     glaubt
    -0.73
    OUG
    -0.73
    circulation
    -0.73
    Wm
    -0.71
     zulassen
    -0.69
    查看
    -0.68
    POSITIVE LOGITS
     rights
    0.91
     couples
    0.89
     marriage
    0.88
    dar
    0.87
     tendencies
    0.85
    iai
    0.84
    bait
    0.84
    siąż
    0.83
    neighbors
    0.83
     clientele
    0.83
    Activations Density 0.018%

    No Known Activations