© 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. 22-GEMMASCOPE-2-RES-262K
    7. 10706
    Prev
    Next
    INDEX
    Explanations

    running and athletics endurance

    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_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     mengakses
    0.78
     sushi
    0.75
     Ansible
    0.74
     guitarra
    0.74
    家具
    0.74
    🎮
    0.73
    Git
    0.71
     muebles
    0.70
     துரு
    0.70
    傀
    0.70
    POSITIVE LOGITS
     sprinting
    2.17
     runners
    1.99
     sprints
    1.96
     runner
    1.96
     sprint
    1.92
    🏃
    1.80
    跑
    1.79
     sprinter
    1.78
     athletics
    1.74
     Athletics
    1.72
    Activations Density 0.104%

    No Known Activations