© 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. 116503
    Prev
    Next
    INDEX
    Explanations

    scanning electron microscopy

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

    scientific imaging techniques, particularly "scanning electron microscopy" and related microscopy methods.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on mentions of “scanning” in the context of microscopy or related technical scanning techniques.

    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
     Seiz
    -0.71
    悵
    -0.70
     Bax
    -0.70
     Dolls
    -0.69
     själva
    -0.69
     Riley
    -0.66
     corporativa
    -0.66
     cottages
    -0.66
     castles
    -0.66
     hires
    -0.65
    POSITIVE LOGITS
    倦
    0.68
     leste
    0.62
    kms
    0.62
     Blackwell
    0.62
    SMART
    0.61
    ូ
    0.61
    eneuve
    0.61
     nej
    0.61
    instantiate
    0.61
    騫
    0.60
    Activations Density 0.066%

    No Known Activations