© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109929
    Prev
    Next
    INDEX
    Explanations

    android UI components and libraries

    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
     BufferedImage
    -0.86
     gewährleisten
    -0.86
    FragmentManager
    -0.84
    TextField
    -0.84
    ליט
    -0.83
    orias
    -0.83
    щается
    -0.81
    ͣ
    -0.81
    tovat
    -0.81
     phénom
    -0.81
    POSITIVE LOGITS
    aried
    0.85
    ridescent
    0.85
     však
    0.83
    atibility
    0.83
     però
    0.82
     vicenda
    0.81
     look
    0.80
    --){
    0.80
     Allerdings
    0.79
     ră
    0.79
    Activations Density 0.002%

    No Known Activations