© 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. 176944
    Prev
    Next
    INDEX
    Explanations

    foreign characters and names

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

    Abstract Syntax Trees and class names

    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
     ਦਵਾਈ
    0.54
     probablement
    0.53
     ਅਤੇ
    0.50
     œuvres
    0.50
     म्हणा
    0.50
     파일을
    0.49
     paroles
    0.48
     እና
    0.46
     inds
    0.46
    𝟑
    0.46
    POSITIVE LOGITS
    Н
    0.53
    ন
    0.48
     Lock
    0.46
     Lamp
    0.44
    Harper
    0.44
    WORLD
    0.43
    Lamp
    0.42
    World
    0.42
    VIC
    0.42
    official
    0.41
    Activations Density 0.001%

    No Known Activations