© 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. 91354
    Prev
    Next
    INDEX
    Explanations

    hall effect sensor

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

    The neuron responds to mentions of electrical power system measurements and high-voltage/high-current components (e.g. voltage, current, transformers, breakers, sensors).

    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
     portefeuille
    -0.84
    Lottery
    -0.81
     inventario
    -0.78
     Decline
    -0.75
     cánh
    -0.75
    rauch
    -0.74
     vox
    -0.74
     voltmeter
    -0.73
    inę
    -0.73
    ellees
    -0.73
    POSITIVE LOGITS
     Rog
    1.17
     pickup
    1.13
     Hall
    1.13
     hall
    1.03
     sensor
    1.01
     trigger
    0.96
     magnetic
    0.93
     relu
    0.93
     pick
    0.92
     signal
    0.92
    Activations Density 0.039%

    No Known Activations