© 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. 999
    Prev
    Next
    INDEX
    Explanations

    changes and updates on events

    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
     panneaux
    -1.65
     ouverture
    -1.63
    
    -1.60
     alluring
    -1.55
     étan
    -1.55
     marchandises
    -1.55
     ét
    -1.52
    🧌
    -1.52
     dargestellt
    -1.48
    鲼
    -1.48
    POSITIVE LOGITS
     with
    2.16
     in
    1.70
     through
    1.66
     between
    1.60
     $
    1.57
    おすすめの
    1.51
     nabízí
    1.48
    赑
    1.45
     increases
    1.43
     ३
    1.41
    Activations Density 0.009%

    No Known Activations