© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    visual acuity

    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
    0
    -4.09
     Some
    -2.83
    
    -2.78
     Those
    -2.75
    会有
    -2.72
     Using
    -2.70
    c
    -2.66
    3
    -2.63
     THIS
    -2.48
     Slightly
    -2.48
    POSITIVE LOGITS
    冏
    2.50
    笪
    2.34
    ☆☆☆☆☆
    2.28
     какая
    2.20
    းက
    2.17
    銠
    2.16
     玻璃
    2.08
    (
    2.00
    ቷ
    2.00
    .'
    1.98
    Activations Density 0.014%

    No Known Activations