© 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. 10-GEMMASCOPE-RES-131K
    7. 47704
    Prev
    Next
    INDEX
    Explanations

    personally identifiable information

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

    The neuron detects terminology related to data protection and confidentiality methods—e.g. encryption, secure computation, anonymization, de-identification, and data linkage safeguards.

    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
     womit
    -1.17
     fleste
    -1.16
     Merch
    -1.14
     müßte
    -1.11
     eneste
    -1.09
     emporio
    -1.09
     næste
    -1.08
    ganan
    -1.08
     ladri
    -1.06
     sodass
    -1.05
    POSITIVE LOGITS
     décé
    1.21
     découv
    1.16
     ersten
    1.16
    uyor
    1.11
     diferencia
    1.09
     για
    1.08
     บาท
    1.06
     one
    1.05
    ită
    1.04
    spyOn
    1.04
    Activations Density 0.051%

    No Known Activations