© 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. 87232
    Prev
    Next
    INDEX
    Explanations

    Gl- prefix words

    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
     preferências
    -2.48
    是很
    -2.47
     luzes
    -2.14
    стью
    -2.09
    ть
    -2.09
    ada
    -2.09
     pedras
    -2.03
    ':
    -2.02
    ás
    -1.98
     politiche
    -1.97
    POSITIVE LOGITS
     také
    2.66
    ?”
    2.64
    錞
    2.34
     aussi
    2.34
    喾
    2.27
    ilihan
    2.22
     thrilling
    2.22
     heed
    2.19
     understand
    2.16
     furious
    2.16
    Activations Density 0.002%

    No Known Activations