© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68260
    Prev
    Next
    INDEX
    Explanations

    code importing libraries

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

    The neuron detects import statements (i.e. lines beginning with the “import” keyword).

    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
     "
    -1.63
    D
    -1.57
    this
    -1.43
    </i>
    -1.41
     —
    -1.34
     keinerlei
    -1.34
    ﾀ
    -1.34
    意思是
    -1.29
     [
    -1.28
     if
    -1.27
    POSITIVE LOGITS
    鲼
    1.70
     插图
    1.67
    綃
    1.63
    桖
    1.63
    尨
    1.60
    傒
    1.59
    woke
    1.56
    鉏
    1.55
    謔
    1.55
    䊳
    1.54
    Activations Density 0.012%

    No Known Activations