© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33089
    Prev
    Next
    INDEX
    Explanations

    informal settlements

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

    The neuron strongly activates on terms referring to informal or marginalized urban spaces (e.g. slums, informal settlements, peri-urban areas, urban dwellers).

    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
     Primaria
    -0.92
    스터
    -0.84
     REGIONAL
    -0.84
    κης
    -0.84
    Igor
    -0.83
    Mä
    -0.83
     isti
    -0.81
     Crunch
    -0.81
     Revista
    -0.80
     переза
    -0.80
    POSITIVE LOGITS
     slum
    1.73
     settlements
    1.61
     settlement
    1.51
     slums
    1.51
     informal
    1.48
     housing
    1.40
     Settlements
    1.24
    settlement
    1.14
    Settlement
    1.10
    Informal
    1.09
    Activations Density 0.047%

    No Known Activations