© 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. 19244
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

    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
     -
    -1.63
        
    -1.40
     lụ
    -1.36
    There
    -1.32
     ordinario
    -1.22
    可以在
    -1.21
     fixa
    -1.20
     enrique
    -1.20
    と思っていた
    -1.20
     ͡°)
    -1.20
    POSITIVE LOGITS
     Scritto
    1.45
     chłop
    1.34
     Bemerkungen
    1.30
    ële
    1.27
     giugno
    1.25
     pidiendo
    1.24
    culaires
    1.22
     essayé
    1.22
    早上
    1.19
     diciendo
    1.18
    Activations Density 0.041%

    No Known Activations