© 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. 108613
    Prev
    Next
    INDEX
    Explanations

    possession

    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
    знес
    -0.83
    那些
    -0.80
    से
    -0.79
    로
    -0.79
     این
    -0.79
    িনি
    -0.78
    лада
    -0.77
    Ṅ
    -0.77
    から
    -0.76
     oluşan
    -0.76
    POSITIVE LOGITS
     his
    2.91
     its
    2.55
     their
    2.42
     your
    2.33
     своего
    1.88
     svého
    1.88
     yours
    1.87
     своей
    1.87
     своих
    1.85
     swojego
    1.84
    Activations Density 0.007%

    No Known Activations