© 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. 119718
    Prev
    Next
    INDEX
    Explanations

    security and finance

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

    economics and finance

    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
     \'
    0.47
     \#
    0.47
    ג
    0.46
     t
    0.42
     tiss
    0.42
    ಫ
    0.42
    \#
    0.42
     Brem
    0.41
     Dashboard
    0.41
     Capability
    0.40
    POSITIVE LOGITS
    
    0.48
    सायनिक
    0.46
     ekonomi
    0.46
     экономики
    0.45
     grafts
    0.45
     तिजारत
    0.45
    defendant
    0.43
    definition
    0.43
    ীবনী
    0.43
    ्याय
    0.42
    Activations Density 0.000%

    No Known Activations