© 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. 242261
    Prev
    Next
    INDEX
    Explanations

    finance and international markets

    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
    pread
    0.51
     εύ
    0.48
    ॰ऍ
    0.47
    Peq
    0.46
    cak
    0.46
     Easier
    0.46
    䢀
    0.46
    i
    0.45
    unakan
    0.45
    fair
    0.45
    POSITIVE LOGITS
     financière
    0.46
     FINANCIAL
    0.45
     shortlist
    0.44
     الجمع
    0.43
     स्पोर्ट्स
    0.43
     finance
    0.43
     emeritus
    0.43
    部門
    0.42
    資金
    0.42
     FINANCE
    0.42
    Activations Density 0.000%

    No Known Activations