© 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. 69909
    Prev
    Next
    INDEX
    Explanations

    freshly processed or obtained

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

    The neuron strongly activates on terms describing industrial or mechanical processes (e.g. mining, smelting, refining, grows, processes, harvest).

    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
     kateg
    -0.96
     creation
    -0.90
     Sprinkle
    -0.84
    瀛
    -0.82
     reorganization
    -0.81
     náv
    -0.81
     deleting
    -0.80
     princí
    -0.80
    wendi
    -0.79
     lép
    -0.78
    POSITIVE LOGITS
     processing
    1.71
     processed
    1.55
    加工
    1.39
     Processing
    1.38
    processed
    1.28
    Processing
    1.27
    Processed
    1.24
     kiln
    1.18
     harvest
    1.13
    processing
    1.13
    Activations Density 0.075%

    No Known Activations