© 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. 81075
    Prev
    Next
    INDEX
    Explanations

    housing displacement developers

    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
    EFAULT
    -0.95
     méxico
    -0.93
    unesse
    -0.91
    NCIS
    -0.89
     rubio
    -0.88
     ciber
    -0.88
     rowspan
    -0.85
    czegó
    -0.85
     beber
    -0.85
    pendenti
    -0.85
    POSITIVE LOGITS
     gent
    1.94
     displacement
    1.70
    Displacement
    1.52
     Displacement
    1.49
    gent
    1.48
     prices
    1.46
     housing
    1.42
     affordability
    1.38
    displacement
    1.34
     developers
    1.34
    Activations Density 0.015%

    No Known Activations