© 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. 14905
    Prev
    Next
    INDEX
    Explanations

    keel, kneel, yml

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

    This neuron is highly responsive to the substring “keel” (i.e. tokens containing k-e-e-l).

    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
    
    -2.84
    ஂ
    -2.42
    
    -2.33
    衚
    -2.22
    ↵↵
    -2.14
    疍
    -2.14
    綃
    -2.08
    韡
    -2.08
    赁
    -2.03
    袮
    -2.03
    POSITIVE LOGITS
     Официальный
    2.39
    檠
    2.27
     Профиль
    2.17
    珖
    2.17
    metery
    2.17
    ſſen
    2.13
     Сайт
    2.13
     keel
    2.08
    ことも
    2.05
    lässlich
    2.05
    Activations Density 0.006%

    No Known Activations