© 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. 55768
    Prev
    Next
    INDEX
    Explanations

    set or setting parameters

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

    The neuron strongly activates on tokens inside code snippets, effectively detecting source‐code segments.

    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
    тору
    -0.94
    setDisabled
    -0.87
    addHeader
    -0.84
    createCell
    -0.82
    に追加
    -0.82
    glGen
    -0.80
    drawText
    -0.79
    addItem
    -0.79
    startAnimation
    -0.79
    ToList
    -0.79
    POSITIVE LOGITS
     set
    4.31
     setting
    3.91
    设置
    3.39
    set
    3.19
     Set
    3.11
     Setting
    3.03
    Setting
    2.97
    Set
    2.92
     设置
    2.91
     setter
    2.89
    Activations Density 0.200%

    No Known Activations