© 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. 59018
    Prev
    Next
    INDEX
    Explanations

    tab bar controller navigation controller

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

    This neuron activates on mentions of iOS view-controller class names (e.g. TabBarController, NavigationController, ViewController).

    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
     What
    -1.95
     â
    -1.72
     but
    -1.68
    ebles
    -1.63
    ája
    -1.55
    驀
    -1.54
    睨
    -1.54
    各类
    -1.53
    蔑
    -1.44
    鉤
    -1.40
    POSITIVE LOGITS
    不会
    1.53
    2
    1.51
    不能
    1.47
    𝕯
    1.47
    <bos>
    1.47
    6
    1.43
     ACTUALLY
    1.42
     Baumwolle
    1.39
    应该
    1.38
    應該
    1.38
    Activations Density 0.014%

    No Known Activations