© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3082
    Prev
    Next
    INDEX
    Explanations

    electron microscopy

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

    scientific research involving electron microscopy techniques.

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

    This neuron detects references to electron‐microscopy techniques (e.g. “electron microscopy,” “scanning electron,” “transmission electron,” etc.).

    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
     PPT
    -1.04
     confocal
    -0.84
    IVITY
    -0.79
     slides
    -0.78
     Dak
    -0.78
    mensch
    -0.77
     RGB
    -0.76
    addAttribute
    -0.76
     Leinwand
    -0.75
    esomeness
    -0.75
    POSITIVE LOGITS
     electron
    1.40
     Electron
    1.34
    Electron
    1.22
    electron
    1.09
     ELECTRON
    1.07
     TEM
    1.03
     Transmission
    1.00
     grids
    0.99
     EM
    0.92
    TEM
    0.91
    Activations Density 0.108%

    No Known Activations