© 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. 2165
    Prev
    Next
    INDEX
    Explanations

    available apartments for rent

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

    The neuron strongly activates on language characteristic of real-estate rental or sales listings (e.g. mentions of apartments, bedrooms, availability, “to let,” property features, etc.).

    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
     umož
    -0.74
     grandkids
    -0.72
     vendidos
    -0.72
     largeur
    -0.71
     profondeur
    -0.71
    主力
    -0.70
    歌唱
    -0.69
     buyers
    -0.66
    existe
    -0.66
     Deshalb
    -0.66
    POSITIVE LOGITS
     Inspection
    1.17
    Inspection
    1.15
     tenants
    1.02
     tenancy
    1.02
     Ingo
    0.96
     tenant
    0.93
    inspec
    0.90
     Tenants
    0.89
     inspections
    0.88
    odyear
    0.88
    Activations Density 0.004%

    No Known Activations