© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30104
    Prev
    Next
    INDEX
    Explanations

    encryption and SSL

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    isante
    -0.92
     but
    -0.88
     ExecuteAsync
    -0.82
     adapt
    -0.81
    vorous
    -0.80
    攻略
    -0.79
     может
    -0.79
    AccessControl
    -0.79
     could
    -0.77
     carga
    -0.77
    POSITIVE LOGITS
     encryption
    1.70
     SSL
    1.41
     encrypt
    1.29
     encrypted
    1.28
    encrypted
    1.08
     transmitted
    1.07
     your
    1.06
     transmissions
    1.06
     Encryption
    1.06
    Encryption
    1.05
    Activations Density 0.040%

    No Known Activations