© 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. 22-GEMMASCOPE-RES-131K
    7. 130735
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by formal privacy‐style disclaimers stating that data or cookies cannot be used to directly identify a person.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    identifying human information privacy

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     flesta
    -1.14
     turistas
    -1.01
    山的
    -0.99
    льное
    -0.96
    зон
    -0.96
    zać
    -0.94
    낭
    -0.94
     smoky
    -0.93
     noiva
    -0.93
     ambos
    -0.92
    POSITIVE LOGITS
     data
    1.52
     täh
    1.22
     Turquía
    1.12
     privacy
    1.11
     équipes
    1.08
    genheit
    1.08
     akhirnya
    1.07
    utriche
    1.06
     targeting
    1.06
     information
    1.06
    Activations Density 0.018%

    No Known Activations