© 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. 20380
    Prev
    Next
    INDEX
    Explanations

    subject noun after "the"

    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
     however
    -2.59
     etc
    -2.28
    我先
    -2.25
     jedoch
    -2.17
     &
    -2.06
    ↑↑↑</
    -2.03
     bzw
    -2.02
     також
    -2.02
     myös
    -1.99
    鴣
    -1.98
    POSITIVE LOGITS
     consequent
    2.22
     frankly
    2.14
        
    2.13
     sebagainya
    2.11
     whatnot
    2.06
    蔼
    2.05
                             
    2.00
    箆
    2.00
    珅
    2.00
    _
    1.98
    Activations Density 0.089%

    No Known Activations