© 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. 10-GEMMASCOPE-RES-131K
    4. 1406
    Prev
    Next
    INDEX
    Explanations

    ownership

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

    This neuron responds to words and markers of ownership or possession (e.g., “ownership,” “owner,” “chown,” possessive constructions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    菒
    -1.38
     všetky
    -1.33
     všet
    -1.30
    ₣
    -1.29
    čić
    -1.27
    𝐡
    -1.23
    來
    -1.23
     serão
    -1.20
     servem
    -1.20
     учетом
    -1.19
    POSITIVE LOGITS
     if
    1.32
    ᎒
    1.27
     hanya
    1.26
     größten
    1.23
     a
    1.22
    As
    1.20
    urgency
    1.16
    党员
    1.16
    使う
    1.15
     poco
    1.14
    Activations Density 0.189%

    No Known Activations