© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5292
    Prev
    Next
    INDEX
    Explanations

    minister or political official

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

    point here

    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
     Mỗi
    0.63
    ＆
    0.57
     mỗi
    0.57
     부터
    0.57
     μια
    0.56
     thru
    0.55
     WIFI
    0.54
     从
    0.54
     απο
    0.54
     কোন
    0.53
    POSITIVE LOGITS
     budgetary
    0.66
     그다음에
    0.64
     macroeconomic
    0.61
     माननीय
    0.61
     அமைச்சர்
    0.57
     MINISTER
    0.57
    Minister
    0.57
     justiciable
    0.57
    говор
    0.57
     subparagraph
    0.57
    Activations Density 0.053%

    No Known Activations