© 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. 199256
    Prev
    Next
    INDEX
    Explanations

    postal codes and numbers

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

    communication without order

    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
    ذكر
    0.46
     إذا
    0.45
     Brasileira
    0.45
     Recherche
    0.45
    搆
    0.45
     وفي
    0.44
    rica
    0.44
    versorgung
    0.43
     ständig
    0.43
    路的
    0.43
    POSITIVE LOGITS
     acetonitrile
    0.49
     subcluster
    0.49
     ("
    0.48
     assays
    0.47
     shards
    0.47
     hematopoietic
    0.47
    凍
    0.47
    ␊
    0.46
     covalent
    0.46
     excitatory
    0.46
    Activations Density 0.001%

    No Known Activations