© 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. 99660
    Prev
    Next
    INDEX
    Explanations

    introduction or considerations

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

    The neuron consistently fires on the standalone code keyword “type” (as used in JavaScript object properties).

    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
    '
    -1.62
     here
    -1.45
    </h3>
    -1.41
    \
    -1.40
    ↵↵
    -1.38
    U
    -1.37
     
    -1.35
    </blockquote>
    -1.25
    在这里
    -1.22
    s
    -1.20
    POSITIVE LOGITS
    capai
    1.63
     projekty
    1.57
     to
    1.53
    ادامه
    1.53
    تصویر
    1.49
    穽
    1.48
     Есть
    1.45
    شاهد
    1.45
    cakup
    1.43
     stroj
    1.43
    Activations Density 0.000%

    No Known Activations