© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5777
    Prev
    Next
    INDEX
    Explanations

    tax deductions for individuals

    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_31_width_65k_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
     Öffentlichkeit
    0.62
     Lü
    0.61
    酱
    0.61
    实时
    0.61
     구현
    0.60
     Gött
    0.59
     gł
    0.58
    流畅
    0.58
    层
    0.58
    Methylsulfanyl
    0.57
    POSITIVE LOGITS
     taxable
    1.01
     deductible
    0.97
    income
    0.96
     income
    0.95
     eligible
    0.94
     tax
    0.89
     taxed
    0.86
     taxpayers
    0.85
    eligible
    0.85
     taxpayer
    0.85
    Activations Density 0.119%

    No Known Activations