© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1701
    Prev
    Next
    INDEX
    Explanations

    taxed income and rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    Methylsulfanyl
    0.54
    颚
    0.52
    蛋白质
    0.52
    钣
    0.52
    练
    0.52
     ład
    0.51
     Dynamical
    0.51
    rüstung
    0.51
    绸
    0.51
     कैल्शियम
    0.50
    POSITIVE LOGITS
     taxable
    1.45
     tax
    1.42
    tax
    1.31
     taxpayers
    1.31
     taxpayer
    1.29
     taxed
    1.24
    Tax
    1.15
     Tax
    1.13
     income
    1.13
     taxation
    1.11
    Activations Density 0.068%

    No Known Activations