© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14263
    Prev
    Next
    INDEX
    Explanations

    owning and ownership

    np_acts-logits-general · gemini-2.5-flash-lite

    ownership and possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تي
    0.75
    is
    0.68
    。
    0.67
    يند
    0.66
    أي
    0.65
    បញ្ចូល
    0.65
    انيا
    0.64
    ០
    0.64
    માં
    0.64
    𝗎
    0.63
    POSITIVE LOGITS
     ownership
    1.32
    ownership
    1.15
     Ownership
    1.09
     owning
    0.99
    Ownership
    0.99
     owned
    0.97
    owning
    0.96
    owned
    0.94
     स्वामित्व
    0.94
     собственности
    0.84
    Activations Density 0.686%

    No Known Activations