© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76850
    Prev
    Next
    INDEX
    Explanations

    showing or creating context

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

    This neuron detects references to Core Graphics drawing API calls (e.g., CGContext functions and drawing commands).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     verlo
    -0.79
    GEL
    -0.76
     היתה
    -0.75
     inhibition
    -0.75
     Trang
    -0.74
    polizei
    -0.74
    antur
    -0.73
     consented
    -0.73
    減
    -0.72
    grub
    -0.72
    POSITIVE LOGITS
     EO
    0.81
     Show
    0.80
     current
    0.77
     SHOW
    0.76
    Show
    0.75
     initialState
    0.73
    的后
    0.73
    ショウ
    0.73
    artner
    0.72
     θέ
    0.72
    Activations Density 0.008%

    No Known Activations