© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48046
    Prev
    Next
    INDEX
    Explanations

    surveillance and privacy

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

    privacy and surveillance

    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_262k_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
     resilient
    0.40
     نثر
    0.40
     मिताली
    0.40
    producer
    0.38
     driv
    0.37
    走り
    0.37
    搗
    0.37
     élev
    0.37
    ément
    0.37
    跑
    0.37
    POSITIVE LOGITS
     surveillance
    1.20
     Surveillance
    1.14
    監視
    0.98
     spying
    0.97
     privacy
    0.96
     Privacy
    0.95
     surve
    0.94
    Privacy
    0.91
    隐私
    0.91
    privacy
    0.89
    Activations Density 0.131%

    No Known Activations