© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34938
    Prev
    Next
    INDEX
    Explanations

    tax deduction

    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
     계
    0.38
     involuntary
    0.38
     compromiso
    0.38
     imperio
    0.38
    ធ្វ
    0.37
     gagner
    0.37
     Сло
    0.36
     suffoc
    0.36
    ੀ
    0.36
    pay
    0.35
    POSITIVE LOGITS
     deduction
    1.39
     deductions
    1.34
     deduct
    1.30
     Deduction
    1.25
     Dedu
    1.19
     deductible
    1.16
     deducting
    1.11
     deducted
    1.06
     deductive
    1.00
     ded
    0.88
    Activations Density 0.014%

    No Known Activations