© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49766
    Prev
    Next
    INDEX
    Explanations

    cable TV and internet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Diabetic
    0.70
    il
    0.69
    ва
    0.69
    er
    0.66
    et
    0.64
     Dy
    0.64
    ed
    0.64
    𝐟
    0.63
    ey
    0.63
     Wearing
    0.62
    POSITIVE LOGITS
     phonons
    0.63
    alım
    0.60
     destruir
    0.60
     axles
    0.59
     blots
    0.58
     landfills
    0.57
    めでとう
    0.57
    ปรับ
    0.57
     tubules
    0.57
     panahon
    0.57
    Activations Density 0.002%

    No Known Activations