© 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. 10-GEMMASCOPE-RES-131K
    7. 12465
    Prev
    Next
    INDEX
    Explanations

    property crisis tax

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

    The neuron detects mentions of real estate and property taxation, especially terms like “tax,” “property,” “real estate,” and related fiscal context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     varanda
    -1.20
    erializer
    -1.09
     about
    -1.00
    UAGES
    -1.00
     which
    -1.00
     antwortete
    -0.96
    értel
    -0.94
     janvier
    -0.93
     How
    -0.93
    🇺🇸
    -0.93
    POSITIVE LOGITS
     your
    1.20
    yczne
    1.09
    依然
    1.06
     escritora
    1.05
     bailarina
    1.04
     wciąż
    1.04
    Ɵ
    1.04
     yesterday
    1.03
    />,
    1.02
    }.\
    1.02
    Activations Density 0.036%

    No Known Activations