© 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. 107674
    Prev
    Next
    INDEX
    Explanations

    spatial census data

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     야
    -0.85
    toluene
    -0.83
     хоте
    -0.81
    toed
    -0.77
     Remembrance
    -0.77
     spiaggia
    -0.77
    니메이션
    -0.77
     HISTOR
    -0.77
    smh
    -0.76
    opold
    -0.75
    POSITIVE LOGITS
     deprivation
    1.42
     census
    1.34
     neighborhood
    1.20
     Census
    1.17
     area
    1.13
     spatial
    1.08
     neighborhoods
    1.04
     Area
    1.00
     neighbourhood
    0.99
     map
    0.98
    Activations Density 0.073%

    No Known Activations