© 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. 111074
    Prev
    Next
    INDEX
    Explanations

    mirror concepts

    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
    تح
    -0.87
    목
    -0.80
    GLFW
    -0.77
     тү
    -0.77
    itol
    -0.75
     agreed
    -0.73
    oros
    -0.72
    ittle
    -0.72
    Payments
    -0.72
    illez
    -0.71
    POSITIVE LOGITS
     mirror
    4.34
    mirror
    3.70
     mirrored
    3.45
    Mirror
    3.33
     Mirror
    3.31
     MIRROR
    3.19
     mirrors
    2.95
     mirroring
    2.88
     зерка
    2.78
    镜像
    2.59
    Activations Density 0.045%

    No Known Activations