© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77210
    Prev
    Next
    INDEX
    Explanations

    oaths and pledges

    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
    色が
    -0.98
    也不會
    -0.90
     moistur
    -0.87
    かした
    -0.86
    
    -0.85
    Hover
    -0.85
    笵
    -0.85
     málo
    -0.83
    SUFFIX
    -0.83
    TextWatcher
    -0.83
    POSITIVE LOGITS
     allegiance
    2.11
     loyalty
    1.45
     to
    1.29
     on
    1.12
     alleg
    1.05
     never
    1.05
     oaths
    1.04
     vow
    0.98
     not
    0.97
     dedication
    0.94
    Activations Density 0.007%

    No Known Activations