© 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. 22-GEMMASCOPE-RES-131K
    7. 98675
    Prev
    Next
    INDEX
    Explanations

    code headers and properties

    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
     Enkel
    -0.91
    atkan
    -0.91
    了呢
    -0.89
     зді
    -0.88
     Teknologi
    -0.87
    zade
    -0.84
     should
    -0.84
     tyrannical
    -0.84
    จัง
    -0.83
     RequestMethod
    -0.82
    POSITIVE LOGITS
     total
    1.30
     money
    1.00
    lih
    1.00
    total
    0.97
     $
    0.97
     élabor
    0.96
     maravill
    0.96
     nettoy
    0.94
     entsteht
    0.92
    \[
    0.92
    Activations Density 0.011%

    No Known Activations