© 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. 41-GEMMASCOPE-2-RES-262K
    7. 35369
    Prev
    Next
    INDEX
    Explanations

    attracted to, attraction, attracts

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    adjustment
    0.40
    नम
    0.39
    Adjustment
    0.37
    зиден
    0.36
    櫳
    0.36
    ंडन
    0.36
    leness
    0.35
    Uber
    0.35
    措
    0.35
    داول
    0.34
    POSITIVE LOGITS
     attraction
    1.79
    吸引
    1.56
     attracted
    1.52
     Attraction
    1.49
     attracts
    1.48
     attractions
    1.45
     atracción
    1.45
     attract
    1.43
     привлека
    1.40
     attracting
    1.39
    Activations Density 0.006%

    No Known Activations