© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14535
    Prev
    Next
    INDEX
    Explanations

    Coco Crisp, Cocoapods, Cocos2d

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

    This neuron detects occurrences of the substring “coco” (in any capitalization) within tokens.

    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
     hilfre
    -3.02
    氿
    -2.89
     notwendi
    -2.80
     italie
    -2.77
     sorgfäl
    -2.73
     erwor
    -2.69
     Unterschiede
    -2.66
     vorhand
    -2.58
     entspre
    -2.58
    裢
    -2.56
    POSITIVE LOGITS
     «
    3.39
     »
    2.61
     ''
    2.48
    ’
    2.45
    Unlike
    2.44
    Surprisingly
    2.42
    さんは
    2.39
    ']
    2.33
    Nearly
    2.19
    ing
    2.17
    Activations Density 0.003%

    No Known Activations