© 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. 10-GEMMASCOPE-RES-131K
    7. 42081
    Prev
    Next
    INDEX
    Explanations

    number 1

    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
    s
    -1.91
    -1.76
     拡大
    -1.75
    v
    -1.68
     estos
    -1.68
    data
    -1.66
     другими
    -1.66
    (
    -1.64
    局长
    -1.62
    _
    -1.60
    POSITIVE LOGITS
    laund
    1.84
    狁
    1.80
    ⬈
    1.65
     wasn
    1.63
    éramos
    1.62
    维持
    1.58
     нашел
    1.57
    感觉到
    1.57
    もありました
    1.56
     завжди
    1.52
    Activations Density 0.057%

    No Known Activations