© 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. 10-GEMMASCOPE-RES-131K
    4. 19175
    Prev
    Next
    INDEX
    Explanations

    nm scale technology

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

    The neuron fires on hardware specification numbers and units (e.g. process‐node “nm” values and model digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    </h2>
    -1.49
     que
    -1.48
     asked
    -1.41
    了一個
    -1.38
     photograph
    -1.38
     byl
    -1.32
    ,’
    -1.31
    !
    -1.31
     two
    -1.30
     one
    -1.29
    POSITIVE LOGITS
    先是
    1.49
    Focusing
    1.45
     olduk
    1.43
    garder
    1.43
     różnych
    1.42
     علام
    1.42
     Apply
    1.38
     yerine
    1.36
     confirmó
    1.34
     menilai
    1.34
    Activations Density 0.022%

    No Known Activations