© 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. 159246
    Prev
    Next
    INDEX
    Explanations

    financial or economic terms

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

    documents, sources, workshop, gently

    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
    必备
    0.56
    细
    0.56
    欣赏
    0.55
    艺术
    0.54
    游泳
    0.54
    Przy
    0.54
    赐
    0.54
     ฉ
    0.54
    滢
    0.54
    ików
    0.54
    POSITIVE LOGITS
     ostensibly
    0.59
     nonprofits
    0.53
     signatories
    0.53
     Reuters
    0.53
     leveraged
    0.53
     pensions
    0.52
     investors
    0.51
     financiers
    0.50
     reforms
    0.50
     creditor
    0.50
    Activations Density 0.008%

    No Known Activations