© 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. 117864
    Prev
    Next
    INDEX
    Explanations

    tax district and levies

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

    The neuron fires on mentions of “tax” (and related fiscal‐district terms), flagging references to taxation or tax districts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    partite
    -0.77
    Laugh
    -0.76
    п
    -0.74
    謄
    -0.71
    ستخدم
    -0.71
     Bias
    -0.71
     记
    -0.71
    dirond
    -0.70
    Bekijk
    -0.70
     foul
    -0.70
    POSITIVE LOGITS
     levy
    1.48
     tax
    1.34
     mills
    1.10
     Levy
    1.06
     property
    1.05
     levies
    1.05
     levied
    1.03
    mills
    1.02
    Levy
    1.00
    levy
    1.00
    Activations Density 0.008%

    No Known Activations