© 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. 90272
    Prev
    Next
    INDEX
    Explanations

    test run status

    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
    ഖ
    -0.81
     Mauritania
    -0.80
     Riders
    -0.80
     Riddle
    -0.76
     linge
    -0.73
     delirium
    -0.73
    берг
    -0.72
    ַת
    -0.71
     rector
    -0.70
    Draft
    -0.68
    POSITIVE LOGITS
     runner
    1.51
     test
    1.31
     running
    1.24
     runners
    1.24
     Test
    1.22
    runner
    1.16
    junit
    1.16
     reporters
    1.13
     reporting
    1.13
    跑
    1.08
    Activations Density 0.116%

    No Known Activations