© 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. 63580
    Prev
    Next
    INDEX
    Explanations

    with preposition following

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

    countries wishing

    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
     tedesco
    0.43
    榖
    0.42
    يان
    0.41
     spécialistes
    0.41
     demos
    0.40
     nutritionist
    0.39
     pharmacists
    0.39
     favoured
    0.38
    okane
    0.37
     روبل
    0.37
    POSITIVE LOGITS
    מוד
    0.49
    យក
    0.45
     Daunting
    0.43
     दूरी
    0.43
    밤
    0.43
    一个人
    0.42
     Crossing
    0.42
     защита
    0.42
    성에
    0.42
    wens
    0.42
    Activations Density 0.000%

    No Known Activations