© 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. 123
    Prev
    Next
    INDEX
    Explanations

    coast and associated places/organizations

    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
    1
    -2.84
    でしたが
    -2.48
    糶
    -2.45
    なんですが
    -2.41
    箆
    -2.31
    嵎
    -2.25
    也得
    -2.25
    ではある
    -2.23
     owing
    -2.19
     compless
    -2.14
    POSITIVE LOGITS
    ↵
    4.81
     '
    3.44
    ti
    2.58
     has
    2.53
     neue
    2.44
    '
    2.44
    家乡
    2.39
    缅
    2.39
    ated
    2.34
    。”
    2.31
    Activations Density 0.009%

    No Known Activations