© 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. 81516
    Prev
    Next
    INDEX
    Explanations

    capital gains tax

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    å
    -0.84
    <tr>
    -0.81
     MP
    -0.79
     bribery
    -0.78
    Deposit
    -0.78
    Matrix
    -0.77
    MP
    -0.77
     Payments
    -0.74
     lenders
    -0.73
    Graduate
    -0.73
    POSITIVE LOGITS
     capital
    1.77
     gains
    1.55
     Capital
    1.47
    capital
    1.42
    Capital
    1.39
     gain
    1.36
     realized
    1.33
     CGT
    1.24
    CAPITAL
    1.22
     selling
    1.19
    Activations Density 0.011%

    No Known Activations