© 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. 110922
    Prev
    Next
    INDEX
    Explanations

    pressure sensors and flow measurement

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

    The neuron strongly activates on numeric tokens and measurement values (e.g. digits, series numbers, specifications), so it’s detecting numbers and technical numeric data.

    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
     Scotia
    -0.84
     GEAR
    -0.80
    leda
    -0.77
    踰
    -0.73
     trách
    -0.73
    allax
    -0.71
    
    -0.71
    worm
    -0.70
    ぐり
    -0.70
     SECRETARY
    -0.69
    POSITIVE LOGITS
     online
    1.06
     probes
    1.05
     probe
    0.98
     inline
    0.98
     measuring
    0.96
     measurement
    0.94
     transmitters
    0.93
    Online
    0.93
    Measurement
    0.91
     онлайн
    0.91
    Activations Density 0.062%

    No Known Activations