© 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. 34-GEMMASCOPE-RES-131K
    7. 102420
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    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
    襖
    -0.87
     testGet
    -0.82
     isInitialized
    -0.80
    dailymail
    -0.80
    tuer
    -0.80
     sintético
    -0.78
    bilirsiniz
    -0.77
    comings
    -0.77
     seien
    -0.75
     Honig
    -0.75
    POSITIVE LOGITS
     graffiti
    0.93
     Ultrasonic
    0.85
     umgesetzt
    0.84
    ỡ
    0.82
    WebApplication
    0.81
    Давайте
    0.81
    üs
    0.79
     alder
    0.79
     equalizer
    0.79
    Manga
    0.78
    Activations Density 0.001%

    No Known Activations