© 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. 75023
    Prev
    Next
    INDEX
    Explanations

    red and reddish colors

    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
    </sup>
    -1.48
     kuwa
    -1.17
    诶
    -1.10
    bbage
    -1.10
    ^{-}
    -1.09
     ida
    -1.09
    
    -1.07
     deus
    -1.06
     crê
    -1.05
    幸好
    -1.05
    POSITIVE LOGITS
     red
    1.42
     červen
    1.34
    Crimson
    1.13
    ↵
    1.09
     đỏ
    1.09
     síntesis
    1.08
     kırmızı
    1.07
    értel
    1.07
     legislación
    1.06
     czerw
    1.05
    Activations Density 0.055%

    No Known Activations