© 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. 37951
    Prev
    Next
    INDEX
    Explanations

    conditioned, event, license

    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
    ৮
    -0.98
     eight
    -0.96
    8
    -0.96
     Eight
    -0.92
    八
    -0.90
    Eight
    -0.88
    eight
    -0.85
    缰
    -0.78
     Of
    -0.77
    ClickListener
    -0.76
    POSITIVE LOGITS
     JG
    0.78
    向
    0.72
    lijck
    0.70
    ා
    0.68
     Piaget
    0.68
    World
    0.67
     solic
    0.66
     Sonar
    0.66
     अधिक
    0.66
    Ticks
    0.66
    Activations Density 0.690%

    No Known Activations