© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23925
    Prev
    Next
    INDEX
    Explanations

    Q: questions and lists

    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
    LineWidth
    -0.79
     گرفتن
    -0.77
    Neck
    -0.77
     damper
    -0.75
     православ
    -0.74
     Orthodox
    -0.73
    云
    -0.72
    ప
    -0.71
     Heavenly
    -0.71
    JOptionPane
    -0.71
    POSITIVE LOGITS
     Progressive
    0.87
     Liberal
    0.85
     clergy
    0.82
    Progressive
    0.81
    progressive
    0.81
     progressive
    0.79
     liberal
    0.79
    liberal
    0.74
     Feier
    0.72
    Liberal
    0.71
    Activations Density 0.021%

    No Known Activations