© 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. 22-GEMMASCOPE-RES-131K
    4. 68276
    Prev
    Next
    INDEX
    Explanations

    designing technical systems and components

    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_22/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
    StatusOK
    -1.02
    Elekt
    -0.90
     rarely
    -0.87
    ramine
    -0.85
     almost
    -0.85
    cated
    -0.84
    ámetro
    -0.84
    وگ
    -0.83
    亲自
    -0.82
    ثیر
    -0.82
    POSITIVE LOGITS
     designs
    1.27
     designed
    1.16
     design
    1.15
     would
    1.11
     devices
    1.07
     technologies
    1.05
     diseñ
    1.04
     разрабо
    1.01
     设计
    0.94
     schemes
    0.93
    Activations Density 0.097%

    No Known Activations