© 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. 75802
    Prev
    Next
    INDEX
    Explanations

    wiper blades

    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
    ฐ
    -0.76
    rice
    -0.75
    ounder
    -0.74
    口腔
    -0.73
    nog
    -0.73
     Cushman
    -0.73
    walla
    -0.72
     erős
    -0.72
    metries
    -0.71
    toise
    -0.71
    POSITIVE LOGITS
     blade
    1.57
     blades
    1.46
     wiper
    1.30
     squee
    1.27
     Blade
    1.23
    Blade
    1.23
    blade
    1.23
     Blades
    1.17
     rubber
    1.10
     streak
    1.10
    Activations Density 0.022%

    No Known Activations