Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7411
    Prev
    Next
    INDEX
    Explanations

    taxes, taxation, revenue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minuti
    1.23
     expectancy
    1.22
     flashbacks
    1.20
    馆
    1.17
    его
    1.17
    тай
    1.14
    館
    1.13
    ্যান্ট
    1.12
     copil
    1.11
    షణ
    1.10
    POSITIVE LOGITS
     taxes
    1.76
     pajak
    1.70
     Taxes
    1.59
     thuế
    1.56
    税
    1.55
     税
    1.51
     payers
    1.49
    payers
    1.49
     taxe
    1.48
     taxation
    1.46
    Activations Density 0.108%

    No Known Activations