© 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. 34-GEMMASCOPE-RES-131K
    7. 63379
    Prev
    Next
    INDEX
    Explanations

    clears screen in graphics

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

    This neuron fires on programming code tokens—especially API/function calls like OpenGL routines.

    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
     depois
    -0.81
     ツイン
    -0.75
     shaw
    -0.73
    inaldi
    -0.72
     housing
    -0.70
     Fahrer
    -0.70
     eğer
    -0.70
    arian
    -0.70
    Kj
    -0.70
    setParameter
    -0.69
    POSITIVE LOGITS
     clear
    2.22
    Clear
    2.16
    clear
    2.05
     Clear
    2.02
     clears
    1.98
    glClear
    1.98
    CLEAR
    1.89
     cleared
    1.86
     background
    1.82
     clearing
    1.80
    Activations Density 0.011%

    No Known Activations