© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75493
    Prev
    Next
    INDEX
    Explanations

    technical code phrases

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

    This neuron specifically detects programming code snippets, firing strongly on code keywords, symbols, and numeric tokens.

    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
    ādā
    -0.75
    tensorflow
    -0.75
     Kork
    -0.73
    𝖽
    -0.72
    addNode
    -0.71
     yoda
    -0.70
    Tarot
    -0.70
    ESSION
    -0.69
    Graves
    -0.68
    Georges
    -0.67
    POSITIVE LOGITS
     Roblox
    1.23
     roblox
    1.00
    Roblox
    0.94
    cripts
    0.93
     tween
    0.92
     scripts
    0.91
     Tween
    0.89
     ROB
    0.88
     humanoid
    0.88
    Scripts
    0.85
    Activations Density 0.011%

    No Known Activations