© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3155
    Prev
    Next
    INDEX
    Explanations

    letters, newsletters, circulars

    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
    énagement
    -0.78
    LAI
    -0.77
     Farmington
    -0.77
    AMER
    -0.77
     hypertrophy
    -0.76
    AXI
    -0.75
     přek
    -0.74
    getElementById
    -0.73
    Tj
    -0.73
    ⁨
    -0.71
    POSITIVE LOGITS
     should
    1.54
     it
    1.17
    should
    1.16
     sinon
    1.15
    sinon
    1.05
     test
    1.04
     tests
    1.01
    chai
    0.95
    mocha
    0.94
     before
    0.92
    Activations Density 0.028%

    No Known Activations