© 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. 10-GEMMASCOPE-RES-131K
    4. 102052
    Prev
    Next
    INDEX
    Explanations

    input and output signals

    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
    .
    -1.94
    </strong>
    -1.83
    <
    -1.71
    킁
    -1.70
    kes
    -1.69
    撹
    -1.69
    {
    -1.64
    trying
    -1.63
    戋
    -1.58
    Whoever
    -1.57
    POSITIVE LOGITS
     with
    2.27
    replyreport
    2.25
     at
    1.99
     of
    1.98
     because
    1.97
    鏨
    1.88
     for
    1.87
    Betyg
    1.82
     Поэтому
    1.80
     murió
    1.77
    Activations Density 0.034%

    No Known Activations