© 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. 73700
    Prev
    Next
    INDEX
    Explanations

    "source"

    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
    RelativeLayout
    -0.84
    Související
    -0.82
    MathML
    -0.77
     Lightroom
    -0.75
    execSQL
    -0.75
    _;
    -0.75
     وحد
    -0.75
    或是
    -0.74
    __);
    -0.71
    waitKey
    -0.71
    POSITIVE LOGITS
     source
    6.72
     Source
    5.84
    Source
    5.72
    source
    5.66
     SOURCE
    4.91
     sources
    4.81
    SOURCE
    4.59
    ource
    4.00
     Sources
    3.91
    sources
    3.88
    Activations Density 0.217%

    No Known Activations