© 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. 102473
    Prev
    Next
    INDEX
    Explanations

    code properties and permissions

    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
    cuba
    -0.94
     tlie
    -0.93
     rând
    -0.88
     then
    -0.86
    -------------</
    -0.84
     tne
    -0.82
     hulle
    -0.81
    .../
    -0.79
     participado
    -0.79
     删除
    -0.79
    POSITIVE LOGITS
    this
    1.30
     this
    1.28
    これは
    1.02
     familiari
    0.95
    これも
    0.91
    了吗
    0.89
    Situated
    0.88
    prompt
    0.87
    但这
    0.85
     terme
    0.83
    Activations Density 0.000%

    No Known Activations