© 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. 55771
    Prev
    Next
    INDEX
    Explanations

    princess and royal titles

    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
    裁判
    -0.81
    ől
    -0.81
    ilius
    -0.80
    ër
    -0.79
     ดี
    -0.78
     sebagian
    -0.76
     beetroot
    -0.76
    ᱾
    -0.76
     zwykle
    -0.75
    Reusable
    -0.74
    POSITIVE LOGITS
    Princess
    1.52
     Princess
    1.45
     princess
    1.28
    es
    1.26
     公主
    1.21
     принце
    1.17
    殿下
    1.16
     Leia
    1.16
    👸
    1.09
     princesse
    1.05
    Activations Density 0.009%

    No Known Activations