© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 959
    Prev
    Next
    INDEX
    Explanations

    travel ride

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     syntactic
    1.01
     semantic
    1.01
     instantiation
    0.95
     isomorphism
    0.91
     isomorphic
    0.89
     instantiate
    0.89
     impurity
    0.89
     textura
    0.89
    =\{
    0.88
     Cortex
    0.87
    POSITIVE LOGITS
     Travel
    2.89
     travel
    2.88
     travelers
    2.75
    Travel
    2.74
     viajeros
    2.67
     traveler
    2.67
     യാത്ര
    2.67
     여행
    2.66
     маршру
    2.65
     travellers
    2.63
    Activations Density 1.949%

    No Known Activations