© 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. 90919
    Prev
    Next
    INDEX
    Explanations

    mining and earthmoving

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

    The neuron strongly activates on technical, domain-specific terms for heavy construction or hydraulic excavation machinery (e.g., “shovel,” “apron,” “loader,” “bucket”).

    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
    эг
    -0.78
     speckled
    -0.76
     helmets
    -0.76
     Đây
    -0.76
     scaffold
    -0.73
     AGRIC
    -0.73
     agri
    -0.73
    bebasan
    -0.72
     agric
    -0.70
     Слова
    -0.69
    POSITIVE LOGITS
     mining
    0.93
    mining
    0.88
     blasted
    0.84
     haul
    0.83
     Mining
    0.77
    жливо
    0.74
     Drag
    0.73
    Mining
    0.73
     drag
    0.72
    isele
    0.71
    Activations Density 0.012%

    No Known Activations