© 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. 193741
    Prev
    Next
    INDEX
    Explanations

    business, finance, and geopolitical terms

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

    steps and context

    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
    ys
    0.49
    adig
    0.49
     auctions
    0.48
    zels
    0.48
    쿨
    0.48
    emain
    0.47
    setText
    0.47
    bg
    0.47
     बैलेंस
    0.46
    vely
    0.46
    POSITIVE LOGITS
     misschien
    0.47
     Ferris
    0.46
    возможно
    0.46
    ка
    0.45
    אָ
    0.44
    كَ
    0.43
    艦
    0.42
     ơn
    0.42
    觀
    0.42
     পেয়ে
    0.42
    Activations Density 0.001%

    No Known Activations