© 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. 64713
    Prev
    Next
    INDEX
    Explanations

    gay marriage conversion therapy

    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
    持久
    -0.79
    Political
    -0.77
     santuario
    -0.75
    privileged
    -0.73
     begrü
    -0.73
    видно
    -0.72
     Political
    -0.71
    政治
    -0.71
    ว์
    -0.71
     political
    -0.69
    POSITIVE LOGITS
     conversion
    0.97
     Conversion
    0.86
     archaic
    0.86
    Conversion
    0.83
     bots
    0.82
     pastors
    0.78
     conversión
    0.77
     colonial
    0.77
    conversion
    0.76
     punishable
    0.76
    Activations Density 0.022%

    No Known Activations