© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3108
    Prev
    Next
    INDEX
    Explanations

    subordinate hierarchy

    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
     our
    -0.79
    MainThread
    -0.76
     owners
    -0.72
    พี่
    -0.71
     grandparents
    -0.70
    ᾱ
    -0.69
    ゆる
    -0.68
    両親
    -0.68
    Amigos
    -0.67
    깊
    -0.67
    POSITIVE LOGITS
     subordinates
    4.38
     subordinate
    4.16
     подчи
    2.89
     subordinated
    2.64
     subordin
    2.48
     subordination
    2.14
     lower
    2.00
    下
    1.88
     below
    1.84
    下の
    1.84
    Activations Density 0.034%

    No Known Activations