© 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. 22-GEMMASCOPE-RES-131K
    7. 34438
    Prev
    Next
    INDEX
    Explanations

    romance and love

    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_22/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
    Inhoud
    -1.21
     ビジネス
    -1.09
     Superhost
    -1.08
    洐
    -1.08
     riso
    -1.05
    ｌ
    -1.05
     تفاوت
    -1.04
    
    -1.04
     中身
    -1.03
    requently
    -1.00
    POSITIVE LOGITS
     romantic
    1.80
     romance
    1.55
     Valentine
    1.29
    romantic
    1.27
     love
    1.26
     roman
    1.23
     couples
    1.16
    loves
    1.09
     one
    1.08
     lovers
    1.08
    Activations Density 0.088%

    No Known Activations