© 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. 34-GEMMASCOPE-RES-131K
    4. 25562
    Prev
    Next
    INDEX
    Explanations

    directory names and paths

    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
     Theile
    -0.79
     veröffentlich
    -0.79
    ^{*}=
    -0.78
    Ār
    -0.78
     funer
    -0.77
     国内
    -0.75
     ipod
    -0.75
     verwal
    -0.75
     überprü
    -0.74
    🍶
    -0.73
    POSITIVE LOGITS
     directory
    3.23
    dir
    2.77
     dir
    2.61
    Dir
    2.55
     folder
    2.50
    目录
    2.36
    DIR
    2.31
    Directory
    2.22
    directory
    2.17
     Dir
    2.02
    Activations Density 0.119%

    No Known Activations