© 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. 10-GEMMASCOPE-RES-131K
    7. 75361
    Prev
    Next
    INDEX
    Explanations

    energy efficiency and insulation

    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_10/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
     in
    -1.54
     diverso
    -1.33
    Chaque
    -1.11
    OrWhiteSpace
    -1.11
     diversa
    -1.11
     چنین
    -1.09
     reciben
    -1.09
     JMenuItem
    -1.08
     conocen
    -1.05
     ViewHolder
    -1.04
    POSITIVE LOGITS
     étan
    1.30
    ğiniz
    1.27
     our
    1.21
    ToEdit
    1.17
    更多的
    1.17
     perpé
    1.16
     sprawia
    1.16
     honte
    1.16
    還有
    1.14
    drage
    1.13
    Activations Density 0.019%

    No Known Activations