© 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. 10-GEMMASCOPE-RES-131K
    4. 19428
    Prev
    Next
    INDEX
    Explanations

    gtkmm, GTK, GtkWidget

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

    The neuron fires on mentions of the GTK (or gtkmm) library, especially when it’s followed by a version number.

    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
    ↵
    -2.61
    us
    -2.28
    
    -2.23
    我们
    -2.14
    𝐓
    -2.06
     In
    -1.98
    我們
    -1.92
    DESCRIPCIÓN
    -1.92
     Sadly
    -1.91
     interdependent
    -1.91
    POSITIVE LOGITS
    queeze
    2.59
    簠
    2.56
    4
    2.56
    atação
    2.52
    9
    2.27
    猻
    2.25
    豨
    2.22
     hochwer
    2.20
    </tfoot>
    2.14
    鬭
    2.13
    Activations Density 0.001%

    No Known Activations