© 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. 25933
    Prev
    Next
    INDEX
    Explanations

    owner, owners

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

    The neuron detects mentions of ownership—words and phrases referring to an owner or owners (e.g., “owners,” “owner,” “property belonging to no apparent owner,” “direct from the owners,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    follower
    -0.95
    employees
    -0.94
    Employees
    -0.91
    employee
    -0.89
    candidate
    -0.89
    Candidate
    -0.85
    operated
    -0.84
     cellules
    -0.82
    teacher
    -0.82
     striker
    -0.81
    POSITIVE LOGITS
     owners
    5.47
     owner
    5.22
    owner
    3.67
     Owner
    3.48
    owners
    3.45
     Owners
    3.45
    Owners
    3.45
    Owner
    3.39
     pemilik
    3.22
     właścic
    3.20
    Activations Density 0.075%

    No Known Activations