© 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. 128183
    Prev
    Next
    INDEX
    Explanations

    tk followed by other words

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

    The neuron fires on mentions of the Tcl/Tk GUI toolkit (e.g. “tk,” “Tcl,” “Tkinter,” “TKAgg,” etc.).

    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
    ↵
    -3.95
    ↵↵
    -3.13
     want
    -2.98
    极为
    -2.95
    </b>
    -2.73
     It
    -2.69
    𓄹
    -2.66
     was
    -2.63
     That
    -2.58
     Not
    -2.56
    POSITIVE LOGITS
     実例
    2.80
    
    2.75
    庒
    2.67
     收納
    2.64
     墊
    2.59
     插图
    2.58
    はじめ
    2.55
    毟
    2.53
     jezt
    2.53
    𐄁
    2.52
    Activations Density 0.009%

    No Known Activations