© 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. 48500
    Prev
    Next
    INDEX
    Explanations

    projects or care services

    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
     MediaQuery
    -1.40
     of
    -1.36
    ом
    -1.33
    ан
    -1.32
    дарю
    -1.27
    ยัง
    -1.20
     сайты
    -1.19
    ındaki
    -1.17
    ↵↵
    -1.14
    ВС
    -1.14
    POSITIVE LOGITS
     how
    1.68
     here
    1.48
    小声
    1.46
    delà
    1.45
     these
    1.40
     vodou
    1.34
     a
    1.33
    ṱ
    1.32
    どれだけ
    1.31
     regulador
    1.27
    Activations Density 0.122%

    No Known Activations