© 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. 562
    Prev
    Next
    INDEX
    Explanations

    experimental stimuli and data acquisition

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

    The neuron fires on technical instrumentation and data‐acquisition terms—i.e. mentions of recording hardware components (e.g. multi­channel systems, electrodes, sensors, EEG/EMG setups).

    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
     Repr
    -0.76
     walks
    -0.72
    metheus
    -0.71
    图像
    -0.71
    qrcode
    -0.70
     measurements
    -0.69
    WALK
    -0.69
    ꒪
    -0.68
     drone
    -0.68
     imágen
    -0.67
    POSITIVE LOGITS
    ixx
    0.96
    伪
    0.91
     stimulus
    0.90
     TTL
    0.85
     Presentation
    0.84
    TTL
    0.83
    ITI
    0.83
    Presentation
    0.82
    xffffff
    0.82
     fMRI
    0.81
    Activations Density 0.108%

    No Known Activations