© 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-16K
    7. 12192
    Prev
    Next
    INDEX
    Explanations

    tax IRS HMRC refund deductible return

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

    tax authorities and taxpayers

    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_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
    ortic
    0.47
    躏
    0.46
     mackerel
    0.46
    橑
    0.46
     swelling
    0.45
     tendons
    0.44
    wrist
    0.44
    Wrist
    0.44
     cylindrical
    0.42
    观看
    0.42
    POSITIVE LOGITS
     tax
    1.37
     IRS
    1.29
     Tax
    1.27
     taxpayers
    1.24
    Tax
    1.21
    稅
    1.21
    tax
    1.20
     taxpayer
    1.20
     HMRC
    1.19
    税
    1.17
    Activations Density 0.214%

    No Known Activations