© 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. 12111
    Prev
    Next
    INDEX
    Explanations

    Police investigate, Q:, welcome to

    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
     Barra
    -0.81
    阎
    -0.81
    ंबर
    -0.78
     moose
    -0.71
    のス
    -0.70
     Croatian
    -0.70
    CASS
    -0.69
     Hain
    -0.68
     cốc
    -0.67
    hancer
    -0.66
    POSITIVE LOGITS
     Lesotho
    1.61
     Highlands
    0.99
    🇱
    0.96
    лета
    0.79
    Les
    0.79
     highlands
    0.78
     sandstone
    0.76
     isShow
    0.73
    tingly
    0.72
    Showing
    0.71
    Activations Density 0.011%

    No Known Activations