© 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. 34-GEMMASCOPE-RES-131K
    4. 66180
    Prev
    Next
    INDEX
    Explanations

    privacy and encryption tools

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

    This neuron strongly activates on proper names and titles—brand names, project or organization names, and other capitalized entity labels.

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

    code and technical documentation, particularly copyright notices, license headers, and software project metadata.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of internet privacy, encryption, and anti-surveillance/security projects and activism, often in open-source or licensing contexts.

    oai_token-act-pair · gpt-5Triggered 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
     régle
    -0.88
    نس
    -0.87
     Henrique
    -0.81
    Globalization
    -0.79
    Cooling
    -0.77
     photosynthetic
    -0.77
    blooded
    -0.77
    خص
    -0.76
     supernatural
    -0.76
     impeachment
    -0.73
    POSITIVE LOGITS
     privacy
    1.23
     Privacy
    1.18
    privacy
    1.05
     PGP
    1.02
    Privacy
    0.99
     Proton
    0.94
     Libre
    0.93
     Tor
    0.91
     Tails
    0.90
     privacidad
    0.90
    Activations Density 0.077%

    No Known Activations