© 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. 106366
    Prev
    Next
    INDEX
    Explanations

    network protocols over protocols

    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
    ʚ
    -0.87
    buntu
    -0.84
    酪
    -0.81
    蠹
    -0.73
    spacing
    -0.73
    实行
    -0.73
    ال
    -0.73
    니메이션
    -0.71
    年初
    -0.71
     Streit
    -0.70
    POSITIVE LOGITS
     HTTP
    2.13
    HTTP
    1.76
     HTTPS
    1.47
     TCP
    1.39
     FTP
    1.27
     REST
    1.25
    http
    1.19
     MQTT
    1.19
    REST
    1.15
     UDP
    1.15
    Activations Density 0.193%

    No Known Activations