© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13164
    Prev
    Next
    INDEX
    Explanations

    housing prices and rental market

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Electrode
    0.47
     χρησιμοποι
    0.43
    气体
    0.43
     باستخدام
    0.41
     wonderfully
    0.40
    诬
    0.40
     szab
    0.39
    甾
    0.39
    끙
    0.39
    geom
    0.39
    POSITIVE LOGITS
     rents
    0.83
     preços
    0.79
     prices
    0.76
     demand
    0.74
     freehold
    0.73
     рынок
    0.72
     market
    0.72
     수요
    0.72
     rental
    0.71
     hotspots
    0.71
    Activations Density 0.009%

    No Known Activations