© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119753
    Prev
    Next
    INDEX
    Explanations

    Electronic systems, places, and abstract concepts

    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
    ׇ
    -2.28
    摆手
    -1.88
     botanique
    -1.88
     camadas
    -1.84
     mengumumkan
    -1.82
    ṝ
    -1.78
     لأنه
    -1.78
     selepas
    -1.75
     magasiner
    -1.73
     الشاشة
    -1.70
    POSITIVE LOGITS
    ּוֹ
    2.13
     السياس
    1.98
    ִּ
    1.93
     my
    1.91
     people
    1.88
     we
    1.88
     it
    1.84
    ַּ
    1.78
     this
    1.75
     and
    1.74
    Activations Density 0.149%

    No Known Activations