© 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. 47632
    Prev
    Next
    INDEX
    Explanations

    U.S. State Department Diplomatic Service

    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
    Typically
    -0.71
    lecteurs
    -0.69
     Silverman
    -0.68
     Typically
    -0.68
    기도
    -0.65
     contact
    -0.65
     möge
    -0.64
     typically
    -0.64
     Sop
    -0.64
    一行
    -0.63
    POSITIVE LOGITS
     consular
    1.16
     Diplomatic
    1.04
     diplomatic
    0.98
     diplomats
    0.91
     дипло
    0.89
     Passport
    0.88
    reprodu
    0.85
     passport
    0.84
    meralda
    0.81
     USAID
    0.81
    Activations Density 0.026%

    No Known Activations