© 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. 22-GEMMASCOPE-RES-131K
    4. 68418
    Prev
    Next
    INDEX
    Explanations

    cocos2d, iPhone, code

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

    The neuron fires on occurrences of the “cocos2d-x” library name (and its variants, e.g. in copyright lines and URLs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     our
    -1.70
     Really
    -1.50
     not
    -1.34
     Very
    -1.29
     Only
    -1.29
     All
    -1.27
     American
    -1.26
    べる
    -1.26
     America
    -1.24
     my
    -1.23
    POSITIVE LOGITS
     图库
    1.29
     doivent
    1.24
     wijn
    1.22
     PHONE
    1.20
     acl
    1.18
     kerst
    1.17
     CRITICAL
    1.16
     voedsel
    1.15
     typhoon
    1.15
    战争
    1.14
    Activations Density 0.011%

    No Known Activations