© 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. 34704
    Prev
    Next
    INDEX
    Explanations

    development project proposals

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

    The neuron detects terms related to building or land‐use projects—words like development, planning, design, and project.

    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
    zyden
    -0.79
     живут
    -0.79
     providence
    -0.78
    痪
    -0.78
    isp
    -0.77
    ➹
    -0.77
     دری
    -0.73
    Pourquoi
    -0.73
     Crist
    -0.73
     verläng
    -0.72
    POSITIVE LOGITS
     proposals
    1.13
     proposal
    1.05
     permit
    1.00
     approvals
    0.99
    proposals
    0.91
     occurring
    0.90
     rights
    0.90
    density
    0.89
     Permit
    0.85
    proposal
    0.83
    Activations Density 0.011%

    No Known Activations