© 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. 78414
    Prev
    Next
    INDEX
    Explanations

    disabled parking permits

    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
    formatie
    -0.85
     coron
    -0.84
    {{/
    -0.82
     egenskaper
    -0.79
     integ
    -0.78
    wanie
    -0.78
     Ooster
    -0.77
    Доро
    -0.74
    Scheduler
    -0.74
     انجام
    -0.74
    POSITIVE LOGITS
     visitor
    1.96
     disabled
    1.81
     handicapped
    1.72
     visitors
    1.68
     handicap
    1.62
    visitor
    1.60
     Visitor
    1.59
    Visitor
    1.38
    disabled
    1.38
     Disabled
    1.33
    Activations Density 0.021%

    No Known Activations