© 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. 23837
    Prev
    Next
    INDEX
    Explanations

    docker images, unexpected token

    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
     matplotlib
    -0.78
    满
    -0.74
    hren
    -0.73
     Bao
    -0.68
    物的
    -0.67
     Fifteen
    -0.66
    可能
    -0.65
     spacing
    -0.65
    eaker
    -0.64
    若
    -0.64
    POSITIVE LOGITS
     Tujuan
    0.80
    django
    0.75
    ün
    0.71
    Здравствуйте
    0.71
    стой
    0.71
    цию
    0.69
    ческому
    0.68
    ciec
    0.67
    TX
    0.66
    Instru
    0.66
    Activations Density 0.571%

    No Known Activations