© 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. 39719
    Prev
    Next
    INDEX
    Explanations

    instantiate or push ViewController

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find programming API method or function names (typically Camel-Case verbs) that trigger actions, such as Push, FXMLLoader, instantiate, or startActivity.

    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
    骜
    -1.58
     vore
    -1.57
     piele
    -1.49
     nowa
    -1.48
    цов
    -1.45
    驁
    -1.44
     aussit
    -1.43
    赑
    -1.43
    McGraw
    -1.42
     certains
    -1.41
    POSITIVE LOGITS
     of
    1.83
     by
    1.55
     it
    1.46
    in
    1.44
    all
    1.41
     &
    1.41
     from
    1.40
    of
    1.38
    ва
    1.34
     under
    1.27
    Activations Density 0.000%

    No Known Activations