© 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. 33085
    Prev
    Next
    INDEX
    Explanations

    residential units and housing

    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
    raco
    -0.75
     bought
    -0.73
     fortunes
    -0.70
     ritrov
    -0.69
     vic
    -0.68
    ミュージ
    -0.68
     progressed
    -0.67
     AGENTS
    -0.66
    msp
    -0.66
     relocated
    -0.66
    POSITIVE LOGITS
     units
    2.34
     unit
    1.91
     housing
    1.84
    units
    1.83
     Units
    1.71
    Units
    1.67
     UNITS
    1.48
    unit
    1.48
     unités
    1.47
     unidades
    1.43
    Activations Density 0.014%

    No Known Activations