© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5812
    Prev
    Next
    INDEX
    Explanations

    rental car

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Gres
    0.78
     Jones
    0.74
    jones
    0.70
     ಉಪ
    0.69
     Tompkins
    0.68
    Cumm
    0.67
     Goodman
    0.66
    郓
    0.66
     Gron
    0.66
     Jayne
    0.66
    POSITIVE LOGITS
     Car
    1.88
     cars
    1.87
     car
    1.86
    Car
    1.82
     Cars
    1.76
    car
    1.67
    Cars
    1.63
     CAR
    1.57
     voiture
    1.49
     carros
    1.46
    Activations Density 0.075%

    No Known Activations