© 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. 49555
    Prev
    Next
    INDEX
    Explanations

    hours of service regulations

    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
    ⎡
    -0.81
    yafet
    -0.75
    撃
    -0.72
    zegorz
    -0.70
     transpiration
    -0.70
     đứa
    -0.69
    \[
    -0.68
     навсегда
    -0.67
     evaluating
    -0.66
    棻
    -0.66
    POSITIVE LOGITS
     hours
    1.36
     Hours
    1.32
     fatigued
    1.23
     sleeper
    1.18
     HOS
    1.17
    HOS
    1.13
     fatigue
    1.13
     Fatigue
    1.06
    Fatigue
    1.01
     duty
    1.00
    Activations Density 0.011%

    No Known Activations