© 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. 107997
    Prev
    Next
    INDEX
    Explanations

    fines and parking violations

    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
     never
    -1.48
    Never
    -1.16
     Never
    -1.16
     nunca
    -0.97
    never
    -0.94
     provisional
    -0.80
     Absatz
    -0.79
    {~
    -0.77
    nunca
    -0.77
    żli
    -0.75
    POSITIVE LOGITS
    Parking
    1.37
    parking
    1.36
     parking
    1.30
     Parking
    1.24
    停车
    1.01
    运营
    0.98
     BPA
    0.94
    reifen
    0.93
     PARK
    0.88
     keeper
    0.88
    Activations Density 0.004%

    No Known Activations