© 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. 374
    Prev
    Next
    INDEX
    Explanations

    building and construction projects

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

    The neuron predominantly fires on standalone numeric tokens (measurements, counts, money amounts, etc.).

    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
    >--}}
    -1.01
    ayı
    -0.95
    cozy
    -0.93
    cuno
    -0.92
     tärke
    -0.89
     their
    -0.88
    lardan
    -0.87
    larda
    -0.87
    我們
    -0.86
    でしたね
    -0.86
    POSITIVE LOGITS
     construction
    3.84
    construction
    2.81
     Construction
    2.67
    Construction
    2.59
     plans
    2.45
     CONSTRUCTION
    2.39
    CONSTRUCTION
    2.03
     construcción
    1.99
     completion
    1.94
     construção
    1.90
    Activations Density 0.070%

    No Known Activations