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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119072
    Prev
    Next
    INDEX
    Explanations

    tax exclusion, reimbursement arrangements, coronary bypass

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

    text related to financial and tax documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duplo
    -0.82
     Nus
    -0.75
    toMatch
    -0.75
    尽快
    -0.73
    ון
    -0.73
    two
    -0.73
     dupla
    -0.72
    踱
    -0.72
    irat
    -0.72
    Eins
    -0.70
    POSITIVE LOGITS
     employee
    1.76
     employer
    1.68
     Employee
    1.55
     employees
    1.47
     employers
    1.45
     Employer
    1.45
    Employer
    1.38
    Employee
    1.33
     fringe
    1.33
     Fringe
    1.28
    Activations Density 0.015%

    No Known Activations