© 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. 85102
    Prev
    Next
    INDEX
    Explanations

    currency and foreign words

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

    international trade

    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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    0.46
    0.44
     <
    0.42
     runway
    0.42
    嗔
    0.42
    #-
    0.42
     dilihat
    0.41
     word
    0.40
     disco
    0.40
     Geographical
    0.40
    POSITIVE LOGITS
    лайн
    0.60
    𝚛
    0.57
    branchNode
    0.55
    ARS
    0.54
    ensureEqual
    0.54
    echolog
    0.54
     auxqu
    0.52
    wallepics
    0.52
    𝖑
    0.52
     lymphatiques
    0.51
    Activations Density 0.000%

    No Known Activations