© 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. 10-GEMMASCOPE-RES-131K
    7. 90347
    Prev
    Next
    INDEX
    Explanations

    electron microscopy

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

    mentions of electron microscopy and microscopic imaging techniques in scientific texts.

    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_10/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
     внутріш
    -1.40
     figli
    -1.34
    -1.30
    MAXN
    -1.28
    ئت
    -1.24
    est
    -1.24
    S
    -1.24
     入力
    -1.23
     свої
    -1.23
     with
    -1.23
    POSITIVE LOGITS
     inoxydable
    1.52
    »)
    1.44
     куртка
    1.40
     reconn
    1.39
     Perſ
    1.37
     montrent
    1.36
    
    1.36
     aident
    1.36
     WORKING
    1.28
    翃
    1.28
    Activations Density 0.039%

    No Known Activations