© 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. 48002
    Prev
    Next
    INDEX
    Explanations

    command line context

    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
    IQUE
    -0.85
    BufferedWriter
    -0.82
     enters
    -0.81
     diper
    -0.79
     ১
    -0.77
     sonda
    -0.75
    💻
    -0.75
     pò
    -0.75
     obowią
    -0.74
    edia
    -0.74
    POSITIVE LOGITS
     magnificence
    0.77
     тези
    0.71
    清空
    0.70
    刹
    0.68
     Bars
    0.68
    Nutrition
    0.68
    Principles
    0.68
    Eri
    0.68
     卒業
    0.66
     heroic
    0.66
    Activations Density 0.001%

    No Known Activations