© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1654
    Prev
    Next
    INDEX
    Explanations

    impaired driving crashes

    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
    biendo
    -0.93
    arpa
    -0.91
    IsString
    -0.85
     artificiales
    -0.85
     уважением
    -0.85
    褴
    -0.78
     ју
    -0.78
    閉店
    -0.75
     ширина
    -0.73
    density
    -0.73
    POSITIVE LOGITS
     impaired
    1.34
     drunk
    1.32
     distracted
    1.30
     Impaired
    1.13
     statistik
    1.07
     crashes
    1.06
     fatalities
    1.05
     Drunk
    1.03
     Distra
    1.01
     roadways
    1.00
    Activations Density 0.030%

    No Known Activations