© 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. 130526
    Prev
    Next
    INDEX
    Explanations

    programming and biology terms

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

    references to CORS (Cross-Origin Resource Sharing) in web development contexts.

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

    The neuron consistently lights up on occurrences of “CORS” (and related tokens like cors, CrossOrigin, Corsairs), i.e. the acronym or substring “cors” in various contexts.

    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
    峮
    -2.52
     oscu
    -2.44
    푆
    -2.41
     denselben
    -2.41
    蛱
    -2.38
    
    -2.36
    砹
    -2.34
    潆
    -2.20
    ཋ
    -2.16
    蹌
    -2.16
    POSITIVE LOGITS
     neues
    2.95
    s
    2.92
     '
    2.50
    嫆
    2.28
    b
    2.28
    獁
    2.25
    he
    2.22
     знали
    2.20
     the
    2.11
     embalagem
    2.11
    Activations Density 0.001%

    No Known Activations