© 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. 221172
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and quantities

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

    China, ROC, Taiwan perspective

    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
     Fleming
    0.45
     Madame
    0.44
     Pennington
    0.42
     Dan
    0.42
     Bron
    0.42
     Nolan
    0.41
     gazing
    0.41
     Pend
    0.40
     電
    0.40
     Madam
    0.40
    POSITIVE LOGITS
    fathers
    0.58
    años
    0.54
    haul
    0.50
     باپ
    0.46
    tahun
    0.46
    timeouts
    0.46
     उभार
    0.46
    $$_
    0.46
     emoción
    0.45
    تقاوى
    0.45
    Activations Density 0.000%

    No Known Activations