© 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. 22-GEMMASCOPE-RES-131K
    7. 33904
    Prev
    Next
    INDEX
    Explanations

    presenting view controllers or modals

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

    This neuron activates on iOS view-controller presentation code, in particular the terms “present” and names ending in “Controller.”

    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
     \
    -1.19
     "'
    -1.14
     '"
    -1.13
     recém
    -1.11
     apresent
    -1.10
     parfois
    -1.09
     erklärt
    -1.09
     souvent
    -1.08
     atualmente
    -1.06
     bezahlt
    -1.06
    POSITIVE LOGITS
     with
    1.68
    توضیحات
    1.59
     without
    1.57
    معرفی
    1.48
     or
    1.43
    تحميل
    1.40
    دانلود
    1.40
     one
    1.38
    שלום
    1.33
    مقدمه
    1.32
    Activations Density 0.005%

    No Known Activations