© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92392
    Prev
    Next
    INDEX
    Explanations

    construction and contractors

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

    The neuron fires on the very first token of a paragraph or block (i.e. it marks paragraph beginnings).

    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
     стекла
    -0.91
     verrou
    -0.86
    etched
    -0.86
    ственная
    -0.86
    çuk
    -0.84
     caucho
    -0.83
    ప్ర
    -0.83
    partimento
    -0.82
    laß
    -0.81
    Cheese
    -0.79
    POSITIVE LOGITS
     construction
    3.66
     Construction
    3.03
     contractors
    2.84
    construction
    2.83
     contractor
    2.81
    Construction
    2.78
     builders
    2.67
     builder
    2.53
     CONSTRUCTION
    2.38
     строи
    2.34
    Activations Density 0.122%

    No Known Activations