© 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. 185620
    Prev
    Next
    INDEX
    Explanations

    purchases, services, or brands

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

    Bees and acquisition

    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
     deber
    0.50
     fennel
    0.47
     pern
    0.47
    ઔ
    0.46
     partid
    0.46
    ্রেট
    0.46
     powerplant
    0.46
     railroad
    0.45
     comedic
    0.44
     pér
    0.44
    POSITIVE LOGITS
    Distribution
    0.50
     वितरित
    0.49
     गिनती
    0.45
     अधिग्रहण
    0.45
     लूट
    0.44
     पुरा
    0.44
     從
    0.44
    激安
    0.44
     distribusi
    0.44
    distributions
    0.44
    Activations Density 0.000%

    No Known Activations