© 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. 69401
    Prev
    Next
    INDEX
    Explanations

    names like Barney and Arias

    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
    “
    -2.86
    祧
    -2.80
    ``
    -2.56
    .
    -2.55
    ℱ
    -2.52
    .</
    -2.50
    ,'
    -2.42
    .'
    -2.39
    。』
    -2.38
    ۔
    -2.31
    POSITIVE LOGITS
    ar
    2.89
    y
    2.69
    媖
    2.67
    section
    2.61
    geſ
    2.52
    啣
    2.52
    籏
    2.48
    垰
    2.47
    ്ട
    2.44
    TemporalType
    2.36
    Activations Density 0.019%

    No Known Activations