© 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. 34941
    Prev
    Next
    INDEX
    Explanations

    header with charset or file extension

    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
    ၄
    -0.80
     forty
    -0.76
     gegeven
    -0.75
    Dane
    -0.73
    deve
    -0.73
    !!!!!!!!!!!!!!!!
    -0.70
    處理
    -0.69
    dată
    -0.69
    Impressum
    -0.69
    ※
    -0.69
    POSITIVE LOGITS
    7
    1.21
     Zhang
    0.91
    Zhang
    0.87
     sied
    0.82
    <0xE5>
    0.81
     Seven
    0.81
     Seventh
    0.81
    appcompat
    0.76
     VII
    0.76
    $(".
    0.75
    Activations Density 1.581%

    No Known Activations