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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83188
    Prev
    Next
    INDEX
    Explanations

    relationship descriptions

    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
     collaborations
    -0.90
    bonds
    -0.87
     clashes
    -0.85
     bonding
    -0.85
     Contacts
    -0.84
    rete
    -0.82
     connecting
    -0.81
     bonds
    -0.80
    connecting
    -0.79
     mighty
    -0.79
    POSITIVE LOGITS
     relationship
    3.03
    relationship
    2.16
     relación
    2.08
    Relationship
    1.99
     hubungan
    1.98
     Relationship
    1.97
    关系
    1.90
     rapporto
    1.81
     رابطه
    1.79
    關係
    1.77
    Activations Density 0.042%

    No Known Activations