© 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. 34-GEMMASCOPE-RES-131K
    7. 592
    Prev
    Next
    INDEX
    Explanations

    This file

    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_34/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
     sínt
    -0.79
    springer
    -0.75
    写真を
    -0.75
    OrderID
    -0.75
    FRANK
    -0.72
     wobec
    -0.71
    oodle
    -0.70
    immobili
    -0.69
     échou
    -0.69
     lewat
    -0.69
    POSITIVE LOGITS
     file
    3.59
     files
    3.27
    文件
    2.66
    file
    2.44
    ファイル
    2.30
     файл
    2.19
    File
    2.08
     파일
    2.06
     FILE
    2.05
     File
    2.03
    Activations Density 0.417%

    No Known Activations