© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199130
    Prev
    Next
    INDEX
    Explanations

    vehicular access, sea, pricing

    np_acts-logits-general · gemini-2.5-flash-lite

    inflation, expensive, investing, prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ठी
    0.50
    晧
    0.49
    हम
    0.48
    ოთ
    0.48
    अधिकांश
    0.46
     pausa
    0.46
    माही
    0.45
    ਵੀ
    0.44
    ⅳ
    0.44
    בח
    0.44
    POSITIVE LOGITS
     prices
    0.49
     سعر
    0.45
     invest
    0.45
     preços
    0.44
     সম্মেলনে
    0.43
     expenses
    0.42
     destroyed
    0.42
     ¥
    0.42
     عالية
    0.42
     harga
    0.42
    Activations Density 0.001%

    No Known Activations