© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73286
    Prev
    Next
    INDEX
    Explanations

    Gtk, vala, Foundation

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

    The neuron fires on code tokens belonging to GObject/GTK (GNOME) APIs—e.g. identifiers or include‐paths like “gtk,” “g_option_context,” “GError,” “girepository,” 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_22/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
    old
    -1.27
    "
    -1.26
     فقط
    -1.20
     anderen
    -1.19
    >+</
    -1.17
    //
    -1.15
     andere
    -1.14
    ant
    -1.14
    但他
    -1.13
    bf
    -1.12
    POSITIVE LOGITS
    ర్య
    1.33
    melada
    1.28
    绚
    1.22
     Dessa
    1.21
    Pranala
    1.19
     Spisak
    1.17
     Stubbs
    1.16
    āciju
    1.14
     sabias
    1.13
     citada
    1.13
    Activations Density 0.045%

    No Known Activations