© 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. 10983
    Prev
    Next
    INDEX
    Explanations

    money, price, investment

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

    individual financial terms

    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
    简介
    0.42
    词
    0.42
    élène
    0.41
    编
    0.40
     编辑
    0.40
    临床
    0.39
    痈
    0.39
    神经
    0.39
    阃
    0.39
    编辑
    0.39
    POSITIVE LOGITS
     पैसा
    0.56
     dinero
    0.55
    投資
    0.55
    價格
    0.53
    money
    0.53
     money
    0.52
     profite
    0.49
     investment
    0.48
     price
    0.48
     деньги
    0.47
    Activations Density 0.000%

    No Known Activations