© 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. 97774
    Prev
    Next
    INDEX
    Explanations

    mirror and mirrors

    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
     iconst
    -0.87
    瑪
    -0.71
    ЛА
    -0.71
     serce
    -0.69
    idan
    -0.69
    BN
    -0.69
    piración
    -0.69
     Gedächt
    -0.69
    Immun
    -0.68
    레
    -0.67
    POSITIVE LOGITS
     mirror
    4.72
     mirrors
    4.00
    mirror
    3.83
     Mirror
    3.34
    鏡
    3.19
    Mirror
    3.16
     Mirrors
    2.94
    Mirrors
    2.94
     mirrored
    2.88
     MIRROR
    2.84
    Activations Density 0.029%

    No Known Activations