© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127714
    Prev
    Next
    INDEX
    Explanations

    fitness, workout, and physical activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     наслед
    0.38
     песни
    0.38
    дования
    0.38
     oyunc
    0.38
     গান
    0.37
     ಕಡಿ
    0.36
     нож
    0.36
     chơi
    0.35
    Sched
    0.35
    変
    0.35
    POSITIVE LOGITS
    fitness
    0.46
     fitness
    0.45
     Fitness
    0.45
    Fitness
    0.44
    皚
    0.41
    klus
    0.40
     anaer
    0.38
     ades
    0.38
     সাংস
    0.38
    workout
    0.38
    Activations Density 0.000%

    No Known Activations