© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73805
    Prev
    Next
    INDEX
    Explanations

    ownership and property

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

    The neuron fires on legal or financial terms that denote property rights or ownership interests.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     प्रोड
    -1.23
    ↵↵
    -1.13
    styleable
    -1.08
     विश्वसनीय
    -1.06
     afficher
    -1.05
     response
    -0.99
     продолжи
    -0.97
     замет
    -0.97
     referrerpolicy
    -0.96
     affiche
    -0.95
    POSITIVE LOGITS
     ownership
    2.22
     rights
    1.52
     possession
    1.50
    ownership
    1.49
    刹那
    1.19
     balon
    1.16
     propriété
    1.13
     harap
    1.12
    āti
    1.12
    дают
    1.11
    Activations Density 0.019%

    No Known Activations