© 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. 98157
    Prev
    Next
    INDEX
    Explanations

    building construction projects

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

    The neuron strongly activates on tokens that are numeric or contain digits, i.e. references to numbers, dates, project phase codes, and other multi‐digit identifiers.

    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
     renovations
    -0.76
    重点
    -0.73
    ウマ
    -0.72
    TileEntity
    -0.71
    lapia
    -0.69
     renovated
    -0.69
     specialising
    -0.69
    вр
    -0.69
     renovation
    -0.69
    ılar
    -0.69
    POSITIVE LOGITS
     construction
    1.13
    construction
    1.00
    Construction
    1.00
     contractor
    0.98
     Contractor
    0.97
     construc
    0.93
     construcción
    0.93
     Construction
    0.87
     contractors
    0.85
     consortium
    0.83
    Activations Density 0.025%

    No Known Activations