© 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. 119887
    Prev
    Next
    INDEX
    Explanations

    following prepositions or conjunctions

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

    often used or may not

    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
    4
    0.45
    lanır
    0.45
     Kristi
    0.44
    捞
    0.44
     Pharma
    0.44
    ting
    0.44
     Thoughts
    0.44
    rati
    0.44
    lı
    0.43
    费
    0.43
    POSITIVE LOGITS
     ブル
    0.56
     евре
    0.52
    ብስ
    0.51
     отказыва
    0.51
     примене
    0.49
     prothorax
    0.49
     פּ
    0.49
     防止
    0.48
     metastability
    0.47
    })-\
    0.47
    Activations Density 0.002%

    No Known Activations