© 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. 12415
    Prev
    Next
    INDEX
    Explanations

    aesthetic appeal

    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
     retourne
    -1.10
    ཊ
    -1.08
     verhind
    -1.04
     totalement
    -1.03
    
    -1.02
     pricey
    -1.01
     emporter
    -1.01
    ཌ
    -1.00
     sturdy
    -1.00
     diriger
    -1.00
    POSITIVE LOGITS
     aesthetic
    1.22
     aesthetics
    1.09
    Quite
    1.03
     with
    0.98
     in
    0.98
     on
    0.97
     at
    0.97
     “
    0.96
     As
    0.95
     краси
    0.95
    Activations Density 0.105%

    No Known Activations