© 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. 119962
    Prev
    Next
    INDEX
    Explanations

    i ' never

    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
     to
    -2.73
     https
    -1.78
     también
    -1.68
     unserer
    -1.66
     بود
    -1.56
     
    -1.56
     ahora
    -1.55
     tiene
    -1.55
    *}$
    -1.53
     //
    -1.52
    POSITIVE LOGITS
    😚
    1.62
     zowel
    1.57
     susun
    1.55
    覬
    1.55
    😝
    1.54
     spagno
    1.52
    💓
    1.52
     both
    1.52
     mijne
    1.52
    😖
    1.51
    Activations Density 0.067%

    No Known Activations