© 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. 31115
    Prev
    Next
    INDEX
    Explanations

    loyalty and loyal to

    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
    hueta
    -0.79
    ylül
    -0.79
    Erf
    -0.78
    Contacts
    -0.77
    mayın
    -0.77
    Pinterest
    -0.77
    Prede
    -0.76
    Mereka
    -0.75
     sensación
    -0.75
    𝗮
    -0.75
    POSITIVE LOGITS
     loyalty
    4.91
     loyal
    4.63
     Loyalty
    3.75
    Loyalty
    3.64
    loyalty
    3.61
    loyal
    3.42
    忠
    3.33
     faithful
    3.23
     allegiance
    3.14
     Loyal
    3.02
    Activations Density 0.023%

    No Known Activations