© 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. 22-GEMMASCOPE-RES-131K
    7. 53968
    Prev
    Next
    INDEX
    Explanations

    land size and features

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

    The neuron fires on real‐estate size metrics, especially numeric lot or area measurements (e.g. square feet, acres).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.16
     раздра
    -1.05
    或
    -1.03
    cuento
    -1.02
    ✑
    -1.00
    consulté
    -0.99
    或者
    -0.98
    無事に
    -0.97
    是怎么回事
    -0.96
    unsplash
    -0.95
    POSITIVE LOGITS
     weißem
    1.08
     informes
    1.05
     lehetős
    1.02
     posé
    0.99
     ofta
    0.98
     lawn
    0.95
    джан
    0.95
     vaak
    0.94
     fren
    0.94
    前は
    0.93
    Activations Density 0.011%

    No Known Activations