© 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. 10-GEMMASCOPE-RES-131K
    4. 104168
    Prev
    Next
    INDEX
    Explanations

    from in import statements

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

    the keyword "from" in JavaScript/TypeScript import statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on the “from” keyword in import statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    You
    -2.09
    般的
    -2.05
    '
    -1.95
    Ⲉ
    -1.91
    _
    -1.89
    ꜆
    -1.83
    ًا
    -1.83
    ”
    -1.76
     ähnliche
    -1.74
    ’
    -1.73
    POSITIVE LOGITS
    in
    2.06
     ciertamente
    1.95
     and
    1.91
     tecnologías
    1.89
     extremadamente
    1.86
     verdaderamente
    1.76
    triques
    1.75
    ⦊
    1.72
    ebab
    1.71
    趼
    1.70
    Activations Density 0.009%

    No Known Activations