© 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. 90316
    Prev
    Next
    INDEX
    Explanations

    exists or available

    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
     tentu
    -1.09
     bukanlah
    -1.09
    living
    -1.05
     menyukai
    -1.02
     bahagia
    -1.02
    configura
    -1.01
     seseorang
    -1.01
     postup
    -1.00
     menak
    -1.00
    Etimología
    -0.98
    POSITIVE LOGITS
     available
    2.02
     exists
    1.72
     exist
    1.62
     present
    1.57
     OK
    1.48
     ok
    1.41
     gone
    1.41
     intact
    1.38
     alive
    1.38
     needed
    1.37
    Activations Density 0.029%

    No Known Activations