© 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. 93744
    Prev
    Next
    INDEX
    Explanations

    Node.js express application

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Gubernur
    -0.83
     gespannt
    -0.80
     aumentare
    -0.73
     basteln
    -0.73
     Riproduzione
    -0.70
     raided
    -0.69
     rechnen
    -0.69
     vorsichtig
    -0.69
     unsupervised
    -0.69
     juara
    -0.69
    POSITIVE LOGITS
     app
    1.80
    app
    1.33
    Express
    1.28
     express
    1.21
     EXPRESS
    1.20
     server
    1.19
     Express
    1.16
     application
    1.16
     aplik
    1.14
     Flask
    1.10
    Activations Density 0.033%

    No Known Activations