© 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. 31043
    Prev
    Next
    INDEX
    Explanations

    scanning electron microscopy

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

    references to scanning electron microscopy (SEM) and related scientific imaging techniques.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    TRAS
    -0.75
    ekt
    -0.70
    ☼
    -0.69
    kkar
    -0.68
    关心
    -0.68
    🧤
    -0.68
    ]={
    -0.68
    ད་
    -0.66
    Infrared
    -0.66
     sleeping
    -0.65
    POSITIVE LOGITS
     SEM
    1.73
    SEM
    1.48
     accelerating
    0.94
     kV
    0.84
    tação
    0.82
     raster
    0.76
     EDS
    0.75
     SE
    0.74
     Specimen
    0.74
     acceleration
    0.74
    Activations Density 0.037%

    No Known Activations