© 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. 243969
    Prev
    Next
    INDEX
    Explanations

    financial context. leases, applicants, finance, Excel format

    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
     زين
    0.47
     சதவீ
    0.46
     উন্নয়নের
    0.45
     ง่าย
    0.45
     આજે
    0.44
    affaire
    0.44
    존
    0.44
     သူ့
    0.44
     करोड़ों
    0.43
     いた
    0.43
    POSITIVE LOGITS
     topographical
    0.52
     topography
    0.48
     topographic
    0.43
     are
    0.43
     mosques
    0.41
     panoramic
    0.40
     shall
    0.39
    include
    0.38
    шает
    0.38
    瀑
    0.38
    Activations Density 0.000%

    No Known Activations