© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10696
    Prev
    Next
    INDEX
    Explanations

    tax

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

    tax related financial and legal 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_40_width_16k_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
    getBlue
    0.43
    髌
    0.42
    urnya
    0.41
    फेक्शन
    0.41
    кры
    0.40
    temps
    0.40
     ফুলে
    0.40
    τές
    0.40
    űr
    0.39
    ());
    0.39
    POSITIVE LOGITS
    payer
    0.64
     Tax
    0.62
    payers
    0.60
    Tax
    0.59
    iderm
    0.58
     payer
    0.55
     tax
    0.52
     TAX
    0.52
     ট্যাক
    0.52
    paying
    0.52
    Activations Density 0.045%

    No Known Activations