© 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. 63534
    Prev
    Next
    INDEX
    Explanations

    road surface repair

    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
    vain
    -0.79
     Stair
    -0.79
    drawing
    -0.78
    luo
    -0.72
     oral
    -0.71
     apon
    -0.71
    collective
    -0.71
    rox
    -0.71
     السياسة
    -0.71
     eth
    -0.69
    POSITIVE LOGITS
     pavement
    1.55
     pavements
    1.18
     rut
    1.17
     Pavement
    1.14
     Asphalt
    1.05
     trafficking
    0.98
    Traffic
    0.98
    Rut
    0.97
     Pave
    0.93
    rut
    0.93
    Activations Density 0.005%

    No Known Activations